Anshuman Nayak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Anshuman Nayak has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- David C. Weindorf
School of Earth, Environment, and Sustainability, Georgia Southern University, Statesboro, USA
5 shared publications Somsubhra Chakraborty
Agricultural and Food Engineering Department, Indian Institute of Technology Kharagpur, Kharagpur, India
4 shared publications- Somsubhra Chakraborty
Indian Institute of Technology Kharagpur
3 shared publications - Veerabhadrappa Lavanya
Agricultural and Food Engineering Department, Indian Institute of Technology, Kharagpur 721302, India
3 shared publications Bin Li
Louisiana State Univ, Dept Expt Stat, Baton Rouge, LA 70802 USA
2 shared publications- Shubhadip Dasgupta
Department of Agricultural Chemistry and Soil Science, Bidhan Chandra Krishi Viswavidyalaya
2 shared publications
Latest Publications
- Open Access
- 23 July 2026
- Published by Elsevier in Waste Management
- Vol. 224, 115769
Prediction of compost physicochemical properties using image-based feature extraction and machine learning
- 23 July 2026
- Published by Elsevier in Waste Management
- Vol. 224, 115769
Open AccessPrediction of compost physicochemical properties using image-based feature extraction and machine learning
- Open Access
- 13 March 2026
- Published by Copernicus GmbH
Tackling Spatial Heterogeneity in Global Soil Total Carbon Mapping using a Mixture of Localised Experts
Accurate, high-resolution mapping of soil total carbon (TC) stocks on a global scale is fundamental to global carbon cycle modeling, international climate policy (e.g., IPCC inventories), and sustainable land management. Current Digital Soil Mapping (DSM) efforts often rely on monolithic global machine learning models that frequently fail to capture fine-scale local variability and are prone to significant regional biases. These biases stemmed from spatial non-stationarity, disjointed calibration datasets from varied sources, and instrumentation mismatches, leading to poor predictive performance and high uncertainty in under-sampled regions. To address this critical challenge, the Mixture of Localised Experts (MoLE) framework was introduced as a novel deep learning architecture designed for robust and responsible soil property prediction. The MoLE framework overcame the limitations of traditional GLOBAL–LOCAL approaches by employing a dynamic gating network (router) that learned to partition the problem space. This router intelligently directed input data comprising multiple proximal soil sensor features from a multinational dataset to one of several specialised “expert” sub-models. Each “localised expert” was trained to become highly proficient within a specific geographical or data-driven domain, effectively creating a single, cohesive model that “thinks globally but acts locally.” This framework was developed using a large, harmonised proximal sensor dataset (n = 1443) from six countries across five continents to predict TC. When assessed against an independent hold-out validation set, the MoLE framework demonstrated outstanding precision for TC prediction, achieving a coefficient of determination (R²) of 0.98 and a root mean squared error (RMSE) of 0.06%. Crucially, the results indicated that the MoLE architecture substantially reduced regional prediction bias. The interpretable routing mechanism offered fresh perspectives on model decision-making, revealing the experts activated for various ecoregions and boosting the transparency of the model. The MoLE framework offered a scalable, resilient, and comprehensible framework for the advancement of next-generation global soil information systems. By adeptly addressing spatial heterogeneity and reducing regional bias, this methodology represented a substantial advancement in the precise quantification of global TC stocks.
- 13 March 2026
- Published by Copernicus GmbH
Open AccessTackling Spatial Heterogeneity in Global Soil Total Carbon Mapping using a Mixture of Localised Experts
Accurate, high-resolution mapping of soil total carbon (TC) stocks on a global scale is fundamental to global carbon cycle modeling, international climate policy (e.g., IPCC inventories), and sustainable land management. Current Digital Soil Mapping (DSM) efforts often rely on monolithic global machine learning models that frequently fail to capture fine-scale local variability and are prone to significant regional biases. These biases stemmed from spatial non-stationarity, disjointed calibration datasets from varied sources, and instrumentation mismatches, leading to poor predictive performance and high uncertainty in under-sampled regions. To address this critical challenge, the Mixture of Localised Experts (MoLE) framework was introduced as a novel deep learning architecture designed for robust and responsible soil property prediction. The MoLE framework overcame the limitations of traditional GLOBAL–LOCAL approaches by employing a dynamic gating network (router) that learned to partition the problem space. This router intelligently directed input data comprising multiple proximal soil sensor features from a multinational dataset to one of several specialised “expert” sub-models. Each “localised expert” was trained to become highly proficient within a specific geographical or data-driven domain, effectively creating a single, cohesive model that “thinks globally but acts locally.” This framework was developed using a large, harmonised proximal sensor dataset (n = 1443) from six countries across five continents to predict TC. When assessed against an independent hold-out validation set, the MoLE framework demonstrated outstanding precision for TC prediction, achieving a coefficient of determination (R²) of 0.98 and a root mean squared error (RMSE) of 0.06%. Crucially, the results indicated that the MoLE architecture substantially reduced regional prediction bias. The interpretable routing mechanism offered fresh perspectives on model decision-making, revealing the experts activated for various ecoregions and boosting the transparency of the model. The MoLE framework offered a scalable, resilient, and comprehensible framework for the advancement of next-generation global soil information systems. By adeptly addressing spatial heterogeneity and reducing regional bias, this methodology represented a substantial advancement in the precise quantification of global TC stocks.
- Open Access
- 13 March 2026
- Published by Copernicus GmbH
Integrating Proximal and Remote Sensing for Regional Soil Characterization and Mapping in Rural Haiti
Agronomic optimization is essential in developing countries, particularly in regions where soil resources are limited and spatial variability is poorly characterized. This study, the first of its kind in Haiti, applied predictive modeling to link laboratory-derived physical and chemical soil properties with proximal and remotely sensed data collected from 32,949 georeferenced surface soil (0–20 cm) samples across the Arcahaie region. A representative subset of samples (n = 300) was analyzed using multiple machine-learning models, including Random Forest, Gradient Boosting, Stacking Ensemble, and XGBoost, to predict soil pH, texture components (sand, silt, clay), soil organic carbon, soil organic matter, cation exchange capacity, and plant-available P, K, Si, Fe, and Cu from proximal sensing data. Strong predictive performance was achieved for sand, silt, clay, soil organic carbon, soil organic matter, and cation exchange capacity (R² ≥ 0.80), with particularly robust results for soil texture and carbon-related properties, while predictions for other parameters were statistically significant but less accurate. The optimized models were subsequently applied to the full dataset, and spatial interpolation was performed to generate high-resolution maps of soil physical and chemical variability across the region. These outputs provide a decision-support framework for site-specific agronomic management. The methodology demonstrated here is readily transferable to other agriculturally important regions of Haiti and comparable developing-country contexts and could be further extended to three-dimensional modeling and mapping of subsoil properties to better characterize fertility within the root zone.
- 13 March 2026
- Published by Copernicus GmbH
Open AccessIntegrating Proximal and Remote Sensing for Regional Soil Characterization and Mapping in Rural Haiti
Agronomic optimization is essential in developing countries, particularly in regions where soil resources are limited and spatial variability is poorly characterized. This study, the first of its kind in Haiti, applied predictive modeling to link laboratory-derived physical and chemical soil properties with proximal and remotely sensed data collected from 32,949 georeferenced surface soil (0–20 cm) samples across the Arcahaie region. A representative subset of samples (n = 300) was analyzed using multiple machine-learning models, including Random Forest, Gradient Boosting, Stacking Ensemble, and XGBoost, to predict soil pH, texture components (sand, silt, clay), soil organic carbon, soil organic matter, cation exchange capacity, and plant-available P, K, Si, Fe, and Cu from proximal sensing data. Strong predictive performance was achieved for sand, silt, clay, soil organic carbon, soil organic matter, and cation exchange capacity (R² ≥ 0.80), with particularly robust results for soil texture and carbon-related properties, while predictions for other parameters were statistically significant but less accurate. The optimized models were subsequently applied to the full dataset, and spatial interpolation was performed to generate high-resolution maps of soil physical and chemical variability across the region. These outputs provide a decision-support framework for site-specific agronomic management. The methodology demonstrated here is readily transferable to other agriculturally important regions of Haiti and comparable developing-country contexts and could be further extended to three-dimensional modeling and mapping of subsoil properties to better characterize fertility within the root zone.
- Open Access
- 5 October 2024
- Published by Elsevier in Smart Agricultural Technology
- Vol. 9
Digital soil mapping of available phosphorus using a smartphone-integrated RGB imaging device and ascorbic acid extraction method
- 5 October 2024
- Published by Elsevier in Smart Agricultural Technology
- Vol. 9
Open AccessDigital soil mapping of available phosphorus using a smartphone-integrated RGB imaging device and ascorbic acid extraction method
- Open Access
A Smartphone-Enabled Imaging Device for Chromotropic Acid-Based Measurement of Nitrate in Soil Samples
In this study, a novel chromotropic acid-based color development method was proposed for quick estimation of soil nitrate (NO3−). The method utilized a 3D printed device integrated with the rear-end camera of a smartphone and a stand-alone application called SMART NP. By analyzing the mean Value (V) component of the sample’s image, the SMART NP provides instant predictions of soil NO3− levels. The limit of detection was calculated as 0.1 mg L−1 with a sensitivity of 0.26 mg L−1. The device showed a % bias of 0.9% and a precision of 1.95%, indicating its reliability. Additionally, the device-predicted soil NO3− data, combined with kriging interpolation, showcased spatial variability in soil NO3− levels at the regional level. The study employed a Gaussian model of variogram for kriging, and the high Nugget/Sill ratio indicated low spatial autocorrelation, emphasizing the impact of management factors on the spatial distribution of soil NO3− content in the study area. Overall, the imaging device, along with geostatistical interpolation, provided a comprehensive solution for the rapid assessment of spatial variability in soil NO3−content.
Open AccessA Smartphone-Enabled Imaging Device for Chromotropic Acid-Based Measurement of Nitrate in Soil Samples
In this study, a novel chromotropic acid-based color development method was proposed for quick estimation of soil nitrate (NO3−). The method utilized a 3D printed device integrated with the rear-end camera of a smartphone and a stand-alone application called SMART NP. By analyzing the mean Value (V) component of the sample’s image, the SMART NP provides instant predictions of soil NO3− levels. The limit of detection was calculated as 0.1 mg L−1 with a sensitivity of 0.26 mg L−1. The device showed a % bias of 0.9% and a precision of 1.95%, indicating its reliability. Additionally, the device-predicted soil NO3− data, combined with kriging interpolation, showcased spatial variability in soil NO3− levels at the regional level. The study employed a Gaussian model of variogram for kriging, and the high Nugget/Sill ratio indicated low spatial autocorrelation, emphasizing the impact of management factors on the spatial distribution of soil NO3− content in the study area. Overall, the imaging device, along with geostatistical interpolation, provided a comprehensive solution for the rapid assessment of spatial variability in soil NO3−content.
- 1 July 2023
- Published by Elsevier in Microchemical Journal
- Vol. 193
A smartphone-integrated imaging device for measuring nitrate and phosphate in soil and water samples
- 1 July 2023
- Published by Elsevier in Microchemical Journal
- Vol. 193
A smartphone-integrated imaging device for measuring nitrate and phosphate in soil and water samples
- Open Access
- 6 February 2023
- Published by Elsevier in Smart Agricultural Technology
- Vol. 4
Application of smartphone-image processing and transfer learning for rice disease and nutrient deficiency detection
- 6 February 2023
- Published by Elsevier in Smart Agricultural Technology
- Vol. 4
Open AccessApplication of smartphone-image processing and transfer learning for rice disease and nutrient deficiency detection
- Open Access
- 1 January 2001
- Published by Association for Computing Machinery (ACM)
- p. 645-648
Automated synthesis of pipelined designs on FPGAs for signal and image processing applications described in MATLAB
- 1 January 2001
- Published by Association for Computing Machinery (ACM)
- p. 645-648
Open AccessAutomated synthesis of pipelined designs on FPGAs for signal and image processing applications described in MATLAB