Modou Mbaye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Modou Mbaye has a total of 238 co-authors. Here are the top co-authors by number of shared publications:
Arsenio Toloza
6 shared publicationsGerd Dercon
5 shared publications- Peter Strauss
Institut für Kulturtechnik und Bodenwasserhaushalt, Bundesamt für Wasserwirtschaft, Petzenkirchen, Österreich
5 shared publications - Gerhard Rab
Centre of Water Resource Systems, TU Wien, 1040 Vienna, Austria
3 shared publications Hami Said Ahmed
3 shared publicationsLee Kheng Heng
3 shared publications
Latest Publications
- Open Access
- 22 May 2026
- Published by Wiley
End to End High-Throughput Phenotyping of Sorghum Grain Weight Based on Computer Vision
Accurate estimation of sorghum (Sorghum bicolor [L.] Moench) grain yield remains a major bottleneck in breeding programs across sub-Saharan West Africa, where traditional methods rely on manual counting and weighing of grains. These approaches are labor-intensive, time-consuming, and prone to-induced variability, limiting throughput and reproducibility. This study presents an end-to-end high-throughput phenotyping pipeline for automated grain detection and mass estimation using computer vision. The workflow integrates smartphone-based image acquisition, automated foreground extraction, and grain detection using YOLOv11 models, followed by count-to-mass calibration. Three YOLOv11 architectures, small, medium, and large, were evaluated under identical training conditions using transfer learning from COCO pre-trained weights. Among the tested models, the medium configuration provided the best trade-off between precision and detection performance, with precision values reaching up to 0.861. A preprocessing step based on automatic background masking was applied prior to detection, significantly improving robustness under heterogeneous field conditions. Grain count was converted to mass using a linear calibration model. For two locally relevant sorghum elite lines, Faourou and Payenne, strong linear relationships were observed between detected grain number and measured grain weight (R² > 0.998), with mass coefficients k ≈ 0.026 g/grain. To facilitate adoption, a user-friendly R Shiny application was developed, allowing users to upload images, perform automated grain detection, and estimate grain mass using user-defined calibration coefficients. This pipeline provides a scalable and reproducible approach for rapid grain phenotyping and offers strong potential to accelerate selection decisions in sorghum breeding programs under field conditions.
- 22 May 2026
- Published by Wiley
Open AccessEnd to End High-Throughput Phenotyping of Sorghum Grain Weight Based on Computer Vision
Accurate estimation of sorghum (Sorghum bicolor [L.] Moench) grain yield remains a major bottleneck in breeding programs across sub-Saharan West Africa, where traditional methods rely on manual counting and weighing of grains. These approaches are labor-intensive, time-consuming, and prone to-induced variability, limiting throughput and reproducibility. This study presents an end-to-end high-throughput phenotyping pipeline for automated grain detection and mass estimation using computer vision. The workflow integrates smartphone-based image acquisition, automated foreground extraction, and grain detection using YOLOv11 models, followed by count-to-mass calibration. Three YOLOv11 architectures, small, medium, and large, were evaluated under identical training conditions using transfer learning from COCO pre-trained weights. Among the tested models, the medium configuration provided the best trade-off between precision and detection performance, with precision values reaching up to 0.861. A preprocessing step based on automatic background masking was applied prior to detection, significantly improving robustness under heterogeneous field conditions. Grain count was converted to mass using a linear calibration model. For two locally relevant sorghum elite lines, Faourou and Payenne, strong linear relationships were observed between detected grain number and measured grain weight (R² > 0.998), with mass coefficients k ≈ 0.026 g/grain. To facilitate adoption, a user-friendly R Shiny application was developed, allowing users to upload images, perform automated grain detection, and estimate grain mass using user-defined calibration coefficients. This pipeline provides a scalable and reproducible approach for rapid grain phenotyping and offers strong potential to accelerate selection decisions in sorghum breeding programs under field conditions.
- Open Access
- 16 February 2026
- Published by Elsevier in SSRN Electronic Journal
Remotely sensed evapotranspiration enables breeding for improved grain yield and water productivity
The realized rate of genetic gain for grain yield (GY) and water productivity (WP) on-farm depends on the effectiveness of multi-environment trials (METs) to adequately sample the on-farm Target Population of Environments (TPE) and the distribution of on-farm gaps between current and potential yield as constrained by evapotranspiration (ET). Crop modeling permits simulation of genotype-by-environment-by-management combinations that can approximate biophysical limits for GY and WP for the TPE. However, the lack of scalable and cost-effective systems to estimate ET across region-wide METs prevent breeders from mapping their field trials onto the simulated “clouds of the possible” to make deliberate selection decisions for improved WP while selecting for GY. Here we demonstrate an approach that combines CERES-Sorghum, the satellite estimated ET available from OpenET, and GY from a 48 site-years MET. We show that sorghum breeding often operates at near biophysical boundaries, yet breeding gaps persist, creating opportunities to improve WP. Strong lack of correlation for GY among genotype-by-environment interactions could explain low rates of genetic gain for GY reported in grain sorghum. In the absence of deliberate efforts to improve WP, future yield improvement in sorghum will be inevitably tied to increases in water use and underpin the loss of drought tolerance. We conclude the scalable yield-ET gap-analysis methodology introduced here can enable breeders to enhance interpretation of breeding MET results and seek novel opportunities to increase both WP and GY, and that efforts to expand the application domain of the satellite estimated evapotranspiration beyond the U.S. are warranted.
- 16 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRemotely sensed evapotranspiration enables breeding for improved grain yield and water productivity
The realized rate of genetic gain for grain yield (GY) and water productivity (WP) on-farm depends on the effectiveness of multi-environment trials (METs) to adequately sample the on-farm Target Population of Environments (TPE) and the distribution of on-farm gaps between current and potential yield as constrained by evapotranspiration (ET). Crop modeling permits simulation of genotype-by-environment-by-management combinations that can approximate biophysical limits for GY and WP for the TPE. However, the lack of scalable and cost-effective systems to estimate ET across region-wide METs prevent breeders from mapping their field trials onto the simulated “clouds of the possible” to make deliberate selection decisions for improved WP while selecting for GY. Here we demonstrate an approach that combines CERES-Sorghum, the satellite estimated ET available from OpenET, and GY from a 48 site-years MET. We show that sorghum breeding often operates at near biophysical boundaries, yet breeding gaps persist, creating opportunities to improve WP. Strong lack of correlation for GY among genotype-by-environment interactions could explain low rates of genetic gain for GY reported in grain sorghum. In the absence of deliberate efforts to improve WP, future yield improvement in sorghum will be inevitably tied to increases in water use and underpin the loss of drought tolerance. We conclude the scalable yield-ET gap-analysis methodology introduced here can enable breeders to enhance interpretation of breeding MET results and seek novel opportunities to increase both WP and GY, and that efforts to expand the application domain of the satellite estimated evapotranspiration beyond the U.S. are warranted.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Advancing Soil Texture Estimation Across Agricultural Soil Types in Austria Using Portable Gamma-Ray Spectrometry
Soil texture plays a fundamental role in influencing water retention, nutrient dynamics, erosion susceptibility, and carbon sequestration, making it essential for sustainable agricultural practices. Accurate monitoring and mapping of soil texture components, such as clay, silt, and sand, are crucial for effective soil and water management. This study explores the potential of combining radionuclide monitoring data and Gamma-Ray Spectrometry (GRS) with quantitative modelling techniques for soil texture estimation, focusing on transferring a predictive model developed in one location to another.The research builds on work conducted in 2023 at the Hydrological Open-Air Laboratory (HOAL) in Petzenkirchen, Lower Austria, to assess the transferability of a predictive model for soil texture to the experimental farm of the University of Natural Resources and Life Sciences (BOKU) in Raasdorf, near Vienna, Austria. Soil sampling campaigns at Petzenkirchen (2023) and Raasdorf (2024) provided input data for the model. Soil texture was analyzed using the PARIO system, which applies the Integral Suspension Pressure (ISP) method, based on Stokes' law, to determine particle size distributions. Portable gamma-ray spectrometry (GRS) was used to measure activity concentrations of radionuclides (40K, 232Th, and 238U) at multiple locations in each field, serving as predictors for soil texture components through a Python-based statistical model initially developed in Petzenkirchen.The integration of GRS data with quantitative modelling revealed critical relationships between radionuclide concentrations and soil texture components. Moderate positive correlations of 232Th (0.59) and 238U (0.72) with silt, and moderate negative correlations with clay (-0.62 and -0.74), indicate that radionuclides preferentially associate with silt-sized particles due to their larger surface area and mineralogical properties. Additionally, a strong inverse relationship between clay and silt (-0.92) reflects their complementary distribution within the soil matrix. Strong correlations were observed between 238U and both silt (R² = 0.8, p = 4.1 × 10⁻⁵) and clay (R² = 0.78, p = 5.6 × 10⁻⁵) demonstrating its predictive potential. These strong associations formed the basis for selecting 238U as a key predictor for soil texture estimation in Raasdorf.The predictive models from Petzenkirchen were applied to estimate silt and clay content in Raasdorf using 238U as a predictor. The model performed well for silt, achieving a mean error of 10% and an RMSE of 0.07 g, indicating strong agreement between observed and predicted values. However, predictions for clay exhibited greater variability, with a mean error of 25% and an RMSE of 0.28 g. This discrepancy highlights the need for localized calibration to address site-specific differences in soil mineralogy and radionuclide binding affinities between the two fields.This research demonstrates how integrating radionuclide monitoring with quantitative soil texture modeling provides a scalable and cost-effective approach for digital soil mapping in agricultural landscapes. Future work will refine the model by leveraging advanced GRS data analysis, such as radionuclide ratios (e.g., 238U/232Th) and spatial variability, to improve clay predictions and assess uncertainties in soil property estimations. These efforts aim to enhance the applicability of digital soil mapping for precision agriculture and sustainable land management.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessAdvancing Soil Texture Estimation Across Agricultural Soil Types in Austria Using Portable Gamma-Ray Spectrometry
Soil texture plays a fundamental role in influencing water retention, nutrient dynamics, erosion susceptibility, and carbon sequestration, making it essential for sustainable agricultural practices. Accurate monitoring and mapping of soil texture components, such as clay, silt, and sand, are crucial for effective soil and water management. This study explores the potential of combining radionuclide monitoring data and Gamma-Ray Spectrometry (GRS) with quantitative modelling techniques for soil texture estimation, focusing on transferring a predictive model developed in one location to another.The research builds on work conducted in 2023 at the Hydrological Open-Air Laboratory (HOAL) in Petzenkirchen, Lower Austria, to assess the transferability of a predictive model for soil texture to the experimental farm of the University of Natural Resources and Life Sciences (BOKU) in Raasdorf, near Vienna, Austria. Soil sampling campaigns at Petzenkirchen (2023) and Raasdorf (2024) provided input data for the model. Soil texture was analyzed using the PARIO system, which applies the Integral Suspension Pressure (ISP) method, based on Stokes' law, to determine particle size distributions. Portable gamma-ray spectrometry (GRS) was used to measure activity concentrations of radionuclides (40K, 232Th, and 238U) at multiple locations in each field, serving as predictors for soil texture components through a Python-based statistical model initially developed in Petzenkirchen.The integration of GRS data with quantitative modelling revealed critical relationships between radionuclide concentrations and soil texture components. Moderate positive correlations of 232Th (0.59) and 238U (0.72) with silt, and moderate negative correlations with clay (-0.62 and -0.74), indicate that radionuclides preferentially associate with silt-sized particles due to their larger surface area and mineralogical properties. Additionally, a strong inverse relationship between clay and silt (-0.92) reflects their complementary distribution within the soil matrix. Strong correlations were observed between 238U and both silt (R² = 0.8, p = 4.1 × 10⁻⁵) and clay (R² = 0.78, p = 5.6 × 10⁻⁵) demonstrating its predictive potential. These strong associations formed the basis for selecting 238U as a key predictor for soil texture estimation in Raasdorf.The predictive models from Petzenkirchen were applied to estimate silt and clay content in Raasdorf using 238U as a predictor. The model performed well for silt, achieving a mean error of 10% and an RMSE of 0.07 g, indicating strong agreement between observed and predicted values. However, predictions for clay exhibited greater variability, with a mean error of 25% and an RMSE of 0.28 g. This discrepancy highlights the need for localized calibration to address site-specific differences in soil mineralogy and radionuclide binding affinities between the two fields.This research demonstrates how integrating radionuclide monitoring with quantitative soil texture modeling provides a scalable and cost-effective approach for digital soil mapping in agricultural landscapes. Future work will refine the model by leveraging advanced GRS data analysis, such as radionuclide ratios (e.g., 238U/232Th) and spatial variability, to improve clay predictions and assess uncertainties in soil property estimations. These efforts aim to enhance the applicability of digital soil mapping for precision agriculture and sustainable land management.
- Open Access
- 20 January 2025
- Published by Copernicus GmbH
Soil particle size distribution using the integral suspension pressure method (ISP) and gamma-ray spectrometry techniques for soil texture mapping.
Understanding the role of soil texture in soil-water management amid climate change is crucial for sustainable agriculture as it influences water availability, nutrient dynamics, erosion control, carbon sequestration, and overall soil health. Therefore, having soil texture mapping is an important decision tool for establishing sustainable resource management.In this study, we present findings from soil sampling conducted in 2023 and a decade earlier from Hydrological Open-Air Laboratory (HOAL) in Petzenkirchen, Lower Austria. The PARIO system was used to analyse soil particle distribution utilising the Integral Suspension Pressure (ISP) method. This method utilizes the stokes’ law to calculate the particle size distribution based on changes in suspension pressure and temperature. The change of suspension pressure as well the temperature is measured at 10- seconds intervals following the chemical and physical dispersion, along with the pretreatment of soil samples involving the removal of organic matter, soluble salts and determination of sample dry weight. The analysis of soil texture from the 2023 soil sampling, conducted using the PARIO system, revealed a predominant silty clay loam structure, with a particle distribution of 9% sand, 56% silt, and 35% clay, aligning closely with results from a decade prior. Concurrently, we utilized Gamma-Ray Sensor (GRS) technology to measure the spatial activity concentrations (Bq.kg-1) of 40K (potassium), 238U (uranium), and 232Th (thorium) over more 20 points across the fields. The aim was to correlate these radionuclide concentrations with soil texture data using a Python-based correlation model. Preliminary results showed the best correlation between 40K radionuclide concentrations versus clay (R2 = 0.8) and silt (R2 = 0.7) and 238U versus silt (R2= 0.7). Thus, spatial monitoring of 40K and 238U with mobile GRS can be used for spatial determination of clay and silt. Nevertheless, further analysis is essential to compare and validate these results with a more extensive dataset encompassing additional soil texture data.These preliminary results demonstrate the potential of monitoring 40K and 238U concentrations by a portable gamma sensor for soil texture mapping in agricultural land. Further analysis and validation are required to verify the robustness of this model.
- 20 January 2025
- Published by Copernicus GmbH
Open AccessSoil particle size distribution using the integral suspension pressure method (ISP) and gamma-ray spectrometry techniques for soil texture mapping.
Understanding the role of soil texture in soil-water management amid climate change is crucial for sustainable agriculture as it influences water availability, nutrient dynamics, erosion control, carbon sequestration, and overall soil health. Therefore, having soil texture mapping is an important decision tool for establishing sustainable resource management.In this study, we present findings from soil sampling conducted in 2023 and a decade earlier from Hydrological Open-Air Laboratory (HOAL) in Petzenkirchen, Lower Austria. The PARIO system was used to analyse soil particle distribution utilising the Integral Suspension Pressure (ISP) method. This method utilizes the stokes’ law to calculate the particle size distribution based on changes in suspension pressure and temperature. The change of suspension pressure as well the temperature is measured at 10- seconds intervals following the chemical and physical dispersion, along with the pretreatment of soil samples involving the removal of organic matter, soluble salts and determination of sample dry weight. The analysis of soil texture from the 2023 soil sampling, conducted using the PARIO system, revealed a predominant silty clay loam structure, with a particle distribution of 9% sand, 56% silt, and 35% clay, aligning closely with results from a decade prior. Concurrently, we utilized Gamma-Ray Sensor (GRS) technology to measure the spatial activity concentrations (Bq.kg-1) of 40K (potassium), 238U (uranium), and 232Th (thorium) over more 20 points across the fields. The aim was to correlate these radionuclide concentrations with soil texture data using a Python-based correlation model. Preliminary results showed the best correlation between 40K radionuclide concentrations versus clay (R2 = 0.8) and silt (R2 = 0.7) and 238U versus silt (R2= 0.7). Thus, spatial monitoring of 40K and 238U with mobile GRS can be used for spatial determination of clay and silt. Nevertheless, further analysis is essential to compare and validate these results with a more extensive dataset encompassing additional soil texture data.These preliminary results demonstrate the potential of monitoring 40K and 238U concentrations by a portable gamma sensor for soil texture mapping in agricultural land. Further analysis and validation are required to verify the robustness of this model.
- Open Access
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 132626-132643
Improving Pearl Millet Yield Estimation From UAV Imagery in the Semiarid Agroforestry System of Senegal Through Textural Indices and Reflectance Normalization
Enhancing food security in the Sahel through nature-based solutions is urgent given population growth, resource scarcity and climate change. Traditional agroforestry parklands are a farmer- and nature-based widespread form of ecological intensification which randomly integrates trees into crop fields. While most studies estimating crop yields in agroforestry have been conducted in controlled experimental settings, few have addressed the inherent variability in such highly heterogeneous systems. Thus, the purpose of this study is to benefit from a UAV-based proxy-sensing and machine learning approach to address the variability of pearl millet grain yield, according to the distance to randomly distributed trees in a traditional agroforestry system dominated by Faidherbia albida (i.e. groundnut basin of Senegal). 21 vegetation indices (VIs), 32 normalized difference texture indices (NDTIs) derived from multispectral drone images, and normalization variables for radiative conditions were used with yield data collected in 15 plots (around 1 ha each) and subplots (15 m 2 each) displayed at 3 distances from the tree over five cropping seasons (2018 - 2022). In this context, the optimal phenological stage was determined for predicting pearl millet grain yield, which proved to be the pre-heading period. This period was used as the basis for our machine learning model training dataset in the subplots. Two models, Random Forest (RF) and Gradient Boosting Machine (GBM) were compared by combining VIs, NDTIs and normalization variables. GBM was the best-performing model, explaining 78% of observed pearl millet yield variability over five years in the subplots, with a RMSE of 16 g. m −2 . This study revealed that NDTIs calculated from red and green bands were more influential for yield estimation than those based on near-infrared. These results were subsequently used to predict yield in all plots, resulting in a mean relative error of 17.5% between yields estimated by the farmers and GBM-estimated yields. This approach represents a pathway to assessing the withinfield yield variability in highly heterogeneous agroforestry plots and to demonstrate, quantify and optimize tree benefits for ecological intensification.
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 132626-132643
Open AccessImproving Pearl Millet Yield Estimation From UAV Imagery in the Semiarid Agroforestry System of Senegal Through Textural Indices and Reflectance Normalization
Enhancing food security in the Sahel through nature-based solutions is urgent given population growth, resource scarcity and climate change. Traditional agroforestry parklands are a farmer- and nature-based widespread form of ecological intensification which randomly integrates trees into crop fields. While most studies estimating crop yields in agroforestry have been conducted in controlled experimental settings, few have addressed the inherent variability in such highly heterogeneous systems. Thus, the purpose of this study is to benefit from a UAV-based proxy-sensing and machine learning approach to address the variability of pearl millet grain yield, according to the distance to randomly distributed trees in a traditional agroforestry system dominated by Faidherbia albida (i.e. groundnut basin of Senegal). 21 vegetation indices (VIs), 32 normalized difference texture indices (NDTIs) derived from multispectral drone images, and normalization variables for radiative conditions were used with yield data collected in 15 plots (around 1 ha each) and subplots (15 m 2 each) displayed at 3 distances from the tree over five cropping seasons (2018 - 2022). In this context, the optimal phenological stage was determined for predicting pearl millet grain yield, which proved to be the pre-heading period. This period was used as the basis for our machine learning model training dataset in the subplots. Two models, Random Forest (RF) and Gradient Boosting Machine (GBM) were compared by combining VIs, NDTIs and normalization variables. GBM was the best-performing model, explaining 78% of observed pearl millet yield variability over five years in the subplots, with a RMSE of 16 g. m −2 . This study revealed that NDTIs calculated from red and green bands were more influential for yield estimation than those based on near-infrared. These results were subsequently used to predict yield in all plots, resulting in a mean relative error of 17.5% between yields estimated by the farmers and GBM-estimated yields. This approach represents a pathway to assessing the withinfield yield variability in highly heterogeneous agroforestry plots and to demonstrate, quantify and optimize tree benefits for ecological intensification.
- Open Access
- 8 March 2024
- Published by Copernicus GmbH
Advanced soil moisture forecasting using Cosmic Ray Neutron Sensor and Artificial Intelligence (AI)
By the year 2050, the global population is projected to reach 9 billion, intensifying the demand for food production and posing substantial challenges to water resources. In this context, the monitoring and prediction of soil moisture play a pivotal role in adopting precision irrigation and effectively managing agricultural water. Cosmic Ray Neutron Sensors (CRNS), a nuclear technology designed for estimating soil moisture content across extensive areas (up to 40 hectares, contingent on sensor sensitivity and location), have demonstrated potential in supporting agricultural water management, hydrology research, and land surface modeling and could serve this purpose admirably. Using a ten-year dataset of soil moisture records from CRNS in conjunction with weather data, we applied a variety of machine learning and artificial intelligence algorithms, such as support vector machines (SVM), extreme gradient descent boost (XGB), long-short term memory (LSTM), recurrent neural networks (RNN) to forecast soil moisture accurately. Preliminary findings exhibit a promising correlation between the predicted and measured soil moisture. Notably one of the algorithms, the XGB excelled, achieving a coefficient of determination (R2) of 0.67 a root mean square error (RMSE) of 4%, and a mean absolute error (MAE) of 2.7% within 48-hour prediction window in the general scenario. These initial outcomes are encouraging, highlighting the potential fusion of cosmic-ray neutron sensors with artificial intelligence paving the way for a new agriculture era focused on precision irrigation. However, further analysis and validation are required to verify the robustness of this model.
- 8 March 2024
- Published by Copernicus GmbH
Open AccessAdvanced soil moisture forecasting using Cosmic Ray Neutron Sensor and Artificial Intelligence (AI)
By the year 2050, the global population is projected to reach 9 billion, intensifying the demand for food production and posing substantial challenges to water resources. In this context, the monitoring and prediction of soil moisture play a pivotal role in adopting precision irrigation and effectively managing agricultural water. Cosmic Ray Neutron Sensors (CRNS), a nuclear technology designed for estimating soil moisture content across extensive areas (up to 40 hectares, contingent on sensor sensitivity and location), have demonstrated potential in supporting agricultural water management, hydrology research, and land surface modeling and could serve this purpose admirably. Using a ten-year dataset of soil moisture records from CRNS in conjunction with weather data, we applied a variety of machine learning and artificial intelligence algorithms, such as support vector machines (SVM), extreme gradient descent boost (XGB), long-short term memory (LSTM), recurrent neural networks (RNN) to forecast soil moisture accurately. Preliminary findings exhibit a promising correlation between the predicted and measured soil moisture. Notably one of the algorithms, the XGB excelled, achieving a coefficient of determination (R2) of 0.67 a root mean square error (RMSE) of 4%, and a mean absolute error (MAE) of 2.7% within 48-hour prediction window in the general scenario. These initial outcomes are encouraging, highlighting the potential fusion of cosmic-ray neutron sensors with artificial intelligence paving the way for a new agriculture era focused on precision irrigation. However, further analysis and validation are required to verify the robustness of this model.
- Open Access
- 15 May 2023
- Published by Copernicus GmbH
Mobile Gamma-ray spectrometry for soil texture mapping
Particle size distribution in soil, or texture, is a property essential for understanding processes driving soil water dynamics, fertility and conservation. However, soil texture mapping, using traditional soil sampling and analytical techniques, is labor intensive, time consuming and hence expensive. Having a more rapid and low-cost proximal sensing technique to accurately map soil texture would be a big step forward, in particular at a sufficiently detailed spatial scale for providing advice on soil management at field scale.For the development of such proximal sensing techniques assisting in soil texture monitoring, a study was carried out by the Joint FAO/IAEA Centre at the Petzenkirchen catchment of the Hydrological Open-Air Laboratory (HOAL), located 100 km west from Vienna in Lower Austria. As sensing technique for determining texture, with emphasis on the topsoil (0-30 cm), Gamma-Ray Sensor (GRS) technology was selected. A Medusa MS-350 portable GRS was used to measure the spatial activity concentrations (Bq.kg-1) of 40K (potassium), 238U (uranium), and 232Th (thorium) over 20 points across the studied catchment. These activity concentrations were then linked with soil texture parameters of interest, such as silt, clay, and sand, at the same positions. In total 200 soil samples (10 soil samples for each of the 20 points) were taken for soil texture determination.Preliminary results showed the best correlation between 40K radionuclide concentrations and clay (R2 = 0.51), and silt (R2 = 0.46). Thus, spatial monitoring of 40K with mobile GRS shows potential for the monitoring of clay and silt. However, correlations with other radionuclides concentrations such as 238U and 232Th were weak with R2 coefficients less than 0.16.Further studies are now required to assess ways to improve 40K based predictability of soil texture and validate the applicability of this approach in a more generic way, i.e. a wide range of soil textures. This validation will then enable the further development of this nuclear technology for effective and efficient ground based and air-borne soil texture determination.
- 15 May 2023
- Published by Copernicus GmbH
Open AccessMobile Gamma-ray spectrometry for soil texture mapping
Particle size distribution in soil, or texture, is a property essential for understanding processes driving soil water dynamics, fertility and conservation. However, soil texture mapping, using traditional soil sampling and analytical techniques, is labor intensive, time consuming and hence expensive. Having a more rapid and low-cost proximal sensing technique to accurately map soil texture would be a big step forward, in particular at a sufficiently detailed spatial scale for providing advice on soil management at field scale.For the development of such proximal sensing techniques assisting in soil texture monitoring, a study was carried out by the Joint FAO/IAEA Centre at the Petzenkirchen catchment of the Hydrological Open-Air Laboratory (HOAL), located 100 km west from Vienna in Lower Austria. As sensing technique for determining texture, with emphasis on the topsoil (0-30 cm), Gamma-Ray Sensor (GRS) technology was selected. A Medusa MS-350 portable GRS was used to measure the spatial activity concentrations (Bq.kg-1) of 40K (potassium), 238U (uranium), and 232Th (thorium) over 20 points across the studied catchment. These activity concentrations were then linked with soil texture parameters of interest, such as silt, clay, and sand, at the same positions. In total 200 soil samples (10 soil samples for each of the 20 points) were taken for soil texture determination.Preliminary results showed the best correlation between 40K radionuclide concentrations and clay (R2 = 0.51), and silt (R2 = 0.46). Thus, spatial monitoring of 40K with mobile GRS shows potential for the monitoring of clay and silt. However, correlations with other radionuclides concentrations such as 238U and 232Th were weak with R2 coefficients less than 0.16.Further studies are now required to assess ways to improve 40K based predictability of soil texture and validate the applicability of this approach in a more generic way, i.e. a wide range of soil textures. This validation will then enable the further development of this nuclear technology for effective and efficient ground based and air-borne soil texture determination.
- Open Access
- 15 May 2023
- Published by Copernicus GmbH
Assessment of the Faidherbia albida effect on millet yield using UAV images analysis and geostatistical techniques
Agroforestry, the association between trees/shrubs and crops, a widespread practice in West Africa, is presented as a lever for ecological intensification to optimize cereal yields in the face of strong population growth and the fight against climate change. Within the framework of the EU-DESIRA SustainSAHEL project, we aim to develop techniques to spatially assess the effect of trees on millet yields on an intra-field scale using imagery from an UAV equipped with a multispectral camera combined with geostatistical approaches. Indeed, recent advances in earth observation technologies position the UAV as an effective tool for evaluating the agronomic performance of agroforestry systems and for taking into account the intra-field variability of yields caused by environmental conditions, agricultural practices or the presence of trees (Roupsard and al., 2020 ; Leroux and al., 2022). The objective of this study was to estimate millet yields intra-field variability using UAV and up-to-date geostatistical approaches.The study was carried out over the 2018-2022 cropping seasons in one representative Faidherbia parkland of the groundnut basin of Senegal. To that end, a Random Forest (RF) algorithm was first calibrated to estimate millet yield at sub-plot scale using a thresholding classification to eliminate non-vegetation elements and also to integrate texture data, in order to take into account the spatial relationships between pairs of pixels. Millet yields data and vegetation and textural index from aerial images at a flight height of 25 meters acquired in farmers’ plots were used to calibrate the RF model. The RF model was used to upscale yield at the whole field scale thus allowing to obtain a map of millet yield. Then Voronoï diagram, with Faidherbia as a reference, was applied to each yield map, considering each Voronoï region as a zone of influence of its included Faidherbia. We then applied a transformation and rotation matrix to overlay all the zones of influence of a population of 50 Faidherbia by putting all the trees at the same geographical position. Finally, we build an atlas, which is an average structure representative of a population and which makes possible to detect the patterns and properties of the evolution of the population considered, to evaluate the distance and directional effect of Faidherbia on vegetation index of the population and then on millet yield.The RF model is able to explain between 70 and 90 % of the millet yield variability. Then the analysis has shown that the tree has an influence on the millet stand density with a distance-decay effect from the tree. This stand density is about 60 % around the tree and 30 % at 15m from the tree.Key words : Agroforestry, Uav, Machine learning, Image analysis, Geostatistics, Atlas
- 15 May 2023
- Published by Copernicus GmbH
Open AccessAssessment of the Faidherbia albida effect on millet yield using UAV images analysis and geostatistical techniques
Agroforestry, the association between trees/shrubs and crops, a widespread practice in West Africa, is presented as a lever for ecological intensification to optimize cereal yields in the face of strong population growth and the fight against climate change. Within the framework of the EU-DESIRA SustainSAHEL project, we aim to develop techniques to spatially assess the effect of trees on millet yields on an intra-field scale using imagery from an UAV equipped with a multispectral camera combined with geostatistical approaches. Indeed, recent advances in earth observation technologies position the UAV as an effective tool for evaluating the agronomic performance of agroforestry systems and for taking into account the intra-field variability of yields caused by environmental conditions, agricultural practices or the presence of trees (Roupsard and al., 2020 ; Leroux and al., 2022). The objective of this study was to estimate millet yields intra-field variability using UAV and up-to-date geostatistical approaches.The study was carried out over the 2018-2022 cropping seasons in one representative Faidherbia parkland of the groundnut basin of Senegal. To that end, a Random Forest (RF) algorithm was first calibrated to estimate millet yield at sub-plot scale using a thresholding classification to eliminate non-vegetation elements and also to integrate texture data, in order to take into account the spatial relationships between pairs of pixels. Millet yields data and vegetation and textural index from aerial images at a flight height of 25 meters acquired in farmers’ plots were used to calibrate the RF model. The RF model was used to upscale yield at the whole field scale thus allowing to obtain a map of millet yield. Then Voronoï diagram, with Faidherbia as a reference, was applied to each yield map, considering each Voronoï region as a zone of influence of its included Faidherbia. We then applied a transformation and rotation matrix to overlay all the zones of influence of a population of 50 Faidherbia by putting all the trees at the same geographical position. Finally, we build an atlas, which is an average structure representative of a population and which makes possible to detect the patterns and properties of the evolution of the population considered, to evaluate the distance and directional effect of Faidherbia on vegetation index of the population and then on millet yield.The RF model is able to explain between 70 and 90 % of the millet yield variability. Then the analysis has shown that the tree has an influence on the millet stand density with a distance-decay effect from the tree. This stand density is about 60 % around the tree and 30 % at 15m from the tree.Key words : Agroforestry, Uav, Machine learning, Image analysis, Geostatistics, Atlas
- Open Access
- 18 October 2021
- Published by Wiley in ESS Open Archive
Astrophysics and Planetary science for development in Africa
Africa is a continent with great assets for Astrophysics and Planetology (including astrobiology): skies unpolluted with anthropogenic light, meteorites and impact structures, and vast sedimentary-metamorphic-igneous records of early Earth’ geologic evolution. Aware of these assets, a community of scientists is involved in increasingly ambitious projects. Their original works notably highlight the African scientific heritage, alongside engagement in economic, cultural and societal development. One of the notable achievements of this group is the observation of three stellar occultations by asteroids in Senegal, in direct support of NASA missions of exploration of the Solar System. The first campaign was achieved in August 2018, in support of the flyby of Kuiper belt object Arrokoth by the New Horizons spacecraft. The second and third campaigns, in September 2020 and October 2021, in preparation for the upcoming flybys of Trojan asteroids Polymele and Orus by NASA’s Lucy mission, were led by Senegalese scientists, supported by a few European astronomers. Other notable achievements include fieldwork at potential or known impact structures (including search of tektites in Côte d’Ivoire), providing opportunities for student training and local education. Members of our group have also launched the first popular science magazine on astronomy (in French) (l’Astronomie Afrique). Last, founding the RISE 5A project (Astronomy and Astrophysics Arising Across Africa), with proposal intended to be resubmitted to the Horizon Europe program in 2022, together with some joint educational initiatives linking Egypt and Spain, will hopefully open new opportunities for staff and students exchanges between Europe and Africa. These achievements also impart an enduring engagement of the youth, while reinforcing the role of West African scientists in the scientific, cultural, and economic development of their countries and communities worldwide.
- 18 October 2021
- Published by Wiley in ESS Open Archive
Open AccessAstrophysics and Planetary science for development in Africa
Africa is a continent with great assets for Astrophysics and Planetology (including astrobiology): skies unpolluted with anthropogenic light, meteorites and impact structures, and vast sedimentary-metamorphic-igneous records of early Earth’ geologic evolution. Aware of these assets, a community of scientists is involved in increasingly ambitious projects. Their original works notably highlight the African scientific heritage, alongside engagement in economic, cultural and societal development. One of the notable achievements of this group is the observation of three stellar occultations by asteroids in Senegal, in direct support of NASA missions of exploration of the Solar System. The first campaign was achieved in August 2018, in support of the flyby of Kuiper belt object Arrokoth by the New Horizons spacecraft. The second and third campaigns, in September 2020 and October 2021, in preparation for the upcoming flybys of Trojan asteroids Polymele and Orus by NASA’s Lucy mission, were led by Senegalese scientists, supported by a few European astronomers. Other notable achievements include fieldwork at potential or known impact structures (including search of tektites in Côte d’Ivoire), providing opportunities for student training and local education. Members of our group have also launched the first popular science magazine on astronomy (in French) (l’Astronomie Afrique). Last, founding the RISE 5A project (Astronomy and Astrophysics Arising Across Africa), with proposal intended to be resubmitted to the Horizon Europe program in 2022, together with some joint educational initiatives linking Egypt and Spain, will hopefully open new opportunities for staff and students exchanges between Europe and Africa. These achievements also impart an enduring engagement of the youth, while reinforcing the role of West African scientists in the scientific, cultural, and economic development of their countries and communities worldwide.
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
Deep learning approach for calibrating Cosmic-Ray Neutron Sensors (CRNS) in area-wide soil moisture monitoring
Traditional field calibration of cosmic-Ray neutron sensors (CRNS) for area-wide soil moisture monitoring is based on time-consuming and often expensive soil sample collection and conventional soil moisture measurement. This calibration requires two field campaigns, one under dry and one under wet soil conditions. However, depending on the agro-ecological context more field campaigns may be required for calibration, due to for instance crop biomass water interference. In addition, the current calibration method includes corrections considering several parameters influencing neutron counts, the proxy for soil moisture, such as soil lattice water, organic carbon, and biomass which need to be measured.The main objective of this study is to investigate and develop an alternative calibration method to the currently available field calibration method. To this end, a Deep Learning model architecture under the TensorFlow machine learning framework is used to calibrate the Cosmic-Ray sensor.The Deep Learning model is built with more than 8 years of CRNS data from Petzenkirchen (Austria) and consists of four hidden layers with activation function and a succession of batch normalization. Prior to build the Deep Learning model, data analysis consisting of pertinent variables selection was performed with multivariate statistical analysis of correlation. Among nine features, five were effectively pertinent and included in the machine learning artificial neural network architecture. The five input variables were the raw neutrons counts (N1 and N2), humidity (H), air pressure (P4) and temperature (T7).The preliminary results show a linear regression with an R2 of 0.97 and the model predicted the soil moisture with less than 1% error.These preliminary results are encouraging and proved that a machine learning based method could be a valuable alternative calibration method for CRNS against the current field calibration method.More investigation will be performed to test the model under different agro-ecological conditions, such as Nebraska, USA. Further, additional input variables will be considered in the development of machine learning based models, to bring in agro-ecological information, such as crop cover, growth stage, precipitation related to the CRNS footprint.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessDeep learning approach for calibrating Cosmic-Ray Neutron Sensors (CRNS) in area-wide soil moisture monitoring
Traditional field calibration of cosmic-Ray neutron sensors (CRNS) for area-wide soil moisture monitoring is based on time-consuming and often expensive soil sample collection and conventional soil moisture measurement. This calibration requires two field campaigns, one under dry and one under wet soil conditions. However, depending on the agro-ecological context more field campaigns may be required for calibration, due to for instance crop biomass water interference. In addition, the current calibration method includes corrections considering several parameters influencing neutron counts, the proxy for soil moisture, such as soil lattice water, organic carbon, and biomass which need to be measured.The main objective of this study is to investigate and develop an alternative calibration method to the currently available field calibration method. To this end, a Deep Learning model architecture under the TensorFlow machine learning framework is used to calibrate the Cosmic-Ray sensor.The Deep Learning model is built with more than 8 years of CRNS data from Petzenkirchen (Austria) and consists of four hidden layers with activation function and a succession of batch normalization. Prior to build the Deep Learning model, data analysis consisting of pertinent variables selection was performed with multivariate statistical analysis of correlation. Among nine features, five were effectively pertinent and included in the machine learning artificial neural network architecture. The five input variables were the raw neutrons counts (N1 and N2), humidity (H), air pressure (P4) and temperature (T7).The preliminary results show a linear regression with an R2 of 0.97 and the model predicted the soil moisture with less than 1% error.These preliminary results are encouraging and proved that a machine learning based method could be a valuable alternative calibration method for CRNS against the current field calibration method.More investigation will be performed to test the model under different agro-ecological conditions, such as Nebraska, USA. Further, additional input variables will be considered in the development of machine learning based models, to bring in agro-ecological information, such as crop cover, growth stage, precipitation related to the CRNS footprint.