Giovanni Paolini has a total of 96 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • MLOps for Edge AI: Satellite Sea Ice Detection Test Bed

    by Juan Odriozola, Giovanni Paolini, Markel Flores, Ander Garcia


  • Open Access

    High resolution surface soil moisture microwave products: intercomparison and evaluation over Spain

    by Nadia Ouaadi, Lionel Jarlan, Michel Le Page, Mehrez Zribi, Giovani Paolini, Bouchra Ait Hssaine, Maria Jose Escorihuela, Pascal Fanise, Olivier Merlin, Nicolas Baghdadi, et al.

    Surface soil moisture (SSM) products at high spatial resolution are increasingly available, either from the disaggregation of coarse-resolution products such as SMAP and SMOS, or from high-resolution radar data such as Sentinel-1. In contrast to coarse resolution products, there is a lack of intercomparison studies of high spatial resolution products, which are more relevant for applications requiring the plot scale. In this context, the objective of this work is the evaluation and intercomparison of three high spatial resolution SSM products on a large database of in situ SSM measurements collected on two different sites in the Urgell region (Catalonia, Spain) in 2021. The satellite SSM products are: i) SSMTheia product at the plot scale derived from a synergy of Sentinel-1 and Sentinel-2 using a machine learning algorithm; ii) SSMρ product at 14 m resolution derived from the Sentinel-1 backscattering coefficient and interferometric coherence using a brute-force algorithm; and iii) SSMSMAP20m product at 20 m resolution obtained from the disaggregation of SMAP using Sentinel-3 and Sentinel-2 data. Evaluation of the three products over the entire database showed that SSMTheia and SSMρ yielded a better estimate than SSMSMAP20m, and SSMρ is slightly better than SSMTheia. In particular, the correlation coefficient is higher than 0.4 for 72%, 40% and 27% of the fields using SSMρ, SSMTheia and SSMSMAP20m, respectively. The lower performance of SSMTheia compared to SSMρ is due to the saturation of SSMTheia at 0.3 m3/m3. The time series analysis shows that SSMSMAP20m is able to detect rainfall events occurring at large scale while irrigation at the plot scale are not caught. This is explained by the use of Sentinel-2 reflectances, which are not linked to surface water status, for the disaggregation of Sentinel-3 land surface temperature. The approach can therefore be improved by using high spatial and temporal resolution thermal data in the perspective of new missions such as TRISHNA and LSTM. Finally, the results show that although reasonable estimates are obtained for annual crops using SSMTheia and SSMρ, poor performance is observed for trees, suggesting the need for better representation of canopy components for tree crops in SSM inversion approaches.

  • Open Access

    Retrieving the irrigation actually applied at district scale: assimilating high-resolution Sentinel-1-derived soil moisture data into a FAO-56-based model

    by Pierre Laluet, Luis Enrique Olivera-Guerra, Víctor Altés, Giovanni Paolini, Nadia Ouaadi, Vincent Rivalland, Wouter Dorigo, Lionel Jarlan, Josep Maria Villar, Olivier Merlin

    Irrigation is the most water consuming activity in the world. Knowing the timing and amount of irrigation that is actually applied is therefore fundamental for water managers. However, this information is rarely available at all scales and is subject to large uncertainties due to the wide variety of existing agricultural practices and associated irrigation regimes (full irrigation, deficit irrigation, or over-irrigation). To fill this gap, we propose a two-step approach based on 15 m resolution Sentinel-1 (S1) surface soil moisture (SSM) data to retrieve the actual irrigation at the weekly scale over an entire irrigation district. In a first step, the S1-derived SSM is assimilated into a FAO-56-based crop water balance model (SAMIR) to retrieve for each crop type both the irrigation amount (Idose) and the soil moisture threshold (SMthreshold) at which irrigation is triggered. To do this, a particle filter method is implemented, with particles reset each month to provide time-varying SMthreshold and Idose. In a second step, the retrieved SMthreshold and Idose values are used as input to SAMIR to estimate the weekly irrigation and its uncertainty. The assimilation approach (SSM-ASSIM) is tested over the 8000 hectare Algerri-Balaguer irrigation district located in northeastern Spain, where in situ irrigation data integrating the whole district are available at the weekly scale during 2019. For evaluation, the performance of SSM-ASSIM is compared with that of the default FAO-56 irrigation module (called FAO56-DEF), which sets the SMthreshold to the critical soil moisture value and systematically fills the soil reservoir for each irrigation event. In 2019, with an observed annual irrigation of 687 mm, SSM-ASSIM (FAO56-DEF) shows a root mean square deviation between retrieved and in situ irrigation of 6.7 (8.8) mm week-1, a bias of +0.3 (-1.4) mm week-1, and a Pearson correlation coefficient of 0.88 (0.78). The SSM-ASSIM approach shows great potential for retrieving the weekly water use over extended areas for any irrigation regime, including over-irrigation.


  • Open Access

    White Paper on User Centred Design to Address Challenges in the Design and Creation of Agricultural Data Visualisation Interfaces

    by Paula Gonzalez, Izar Azpiroz, Mikel Zabala, Giovanni Paolini, Mikel Maiza

    The increase in agricultural data has created a need for developing tools that can manage, share, and visualise this information, while also being accessible to farmers. The use of different technical languages, varying needs, and differing objectives for the tools being developed and used creates a gap between technology developers and farmers, leading to inefficient information transfer. Consequently, interfaces are often poorly adapted to the real needs of end-users and lack essential functionality. This white paper aims to propose a User-Centred Design methodology in order to address the challenges encountered in creating interfaces for shared agricultural Data Space Ecosystems. The proposed methodology, an adaptation of ISO 9241:210-2019, highlights the importance of user participation at various stages of the interface design cycle for the creation of user-adaptive technologies.


  • Open Access

    PrISM at Operational Scale: Monitoring Irrigation District Water Use during Droughts

    by Giovanni Paolini, Maria Jose Escorihuela, Joaquim Bellvert, Olivier Merlin, Thierry Pellarin

    Efficient water management strategies are of utmost importance in drought-prone regions, given the fundamental role irrigation plays in avoiding yield losses and food shortages. Traditional methodologies for estimating irrigation amounts face limitations in terms of overall precision and operational scalability. This study proposes to estimate irrigation amounts from soil moisture (SM) data by adapting the PrISM (Precipitation Inferred from Soil Moisture) methodology. The PrISM assimilates SM into a simple Antecedent Precipitation Index (API) model using a particle filter approach, which allows the creation and estimation of irrigation events. The methodology is applied in a semi-arid region in the Ebro basin, located in the north-east of Spain (Catalonia), from 2016 to 2023. Multi-year drought, which started in 2020, particularly affected the region starting from the spring of 2023, which led to significant reductions in irrigation district water allocations in some of the areas of the region. This study demonstrates that the PrISM approach can correctly identify areas where water restrictions were adopted in 2023, and monitor the water usage with good performances and reliable results. When compared with in situ data for 8 consecutive years, PrISM showed a significant person’s correlation between 0.58 and 0.76 and a cumulative weekly root mean squared error (rmse) between 7 and 11 mm. Additionally, PrISM was applied to three irrigation districts with different levels of modernization, due to the different predominant irrigation systems: flood, sprinkler, and drip. This analysis underlined the strengths and limitations of PrISM depending on the irrigation techniques monitored. PrISM has good performances in areas irrigated by sprinkler and flood systems, while difficulties are present over drip irrigated areas, where the very localized and limited irrigation amounts could not be detected from SM observations.


  • Open Access

    Estimating multi-scale irrigation amounts using multi-resolution soil moisture data: A data-driven approach using PrISM

    by Giovanni Paolini, Maria Jose Escorihuela, Olivier Merlin, Pierre Laluet, Joaquim Bellvert, Thierry Pellarin


  • Open Access

    Remotely Sensed Agriculture Drought Indices for Assessing the Impact on Cereal Yield

    by Manel Khlif, Maria José Escorihuela, Aicha Chahbi Bellakanji, Giovanni Paolini, Zohra Lili Chabaane

    This study aims to analyze the potential of different drought indices for identifying drought periods and predicting cereal yield in two semi-arid regions, Lleida in Catalonia and Kairouan in Tunisia, which have similar Mediterranean climates but different agricultural practices. Four drought indices, namely the Soil Moisture Anomaly Index (SMAI), the Vegetation Anomaly Index (VAI), the Evapotranspiration Anomaly Index (EAI), and the Inverse Temperature Anomaly Index (ITAI), were calculated from remote sensing data. Drought periods were identified from 2010/2011 to 2021/2022 based on the aforementioned indices. A correlation study between drought indices and wheat and barley yields was performed in order to select the most informative index and month for yield prediction. In the rainfed cereal area of Lleida, the strongest correlation was found between the EAI and VAI with barley yield (0.91 and 0.83, respectively) at the time of cereal maturity in June. For wheat, the strongest correlation was found between the EAI and VAI (0.75 and 0.72, respectively) at the time of cereal maturity in July. However, the VAI, EAI, and SMAI showed the best performance as an earlier indicator in March with a correlation with barley yield of 0.72, 0.67, and 0.64, respectively; the lowest standard deviation was for the SMAI. For wheat yield, the best earlier indicator was the SMAI in March, showing the highest correlation (0.6) and the lowest standard deviation. For the irrigated cereal zone of Kairouan, the strongest correlation (0.9) and the lowest standard deviation are found between the EAI and cereal yield in April. In terms of advanced prediction, the VAI shows a high correlation in March (0.79) while the SMAI shows a slightly lower correlation in February (0.67) and a lower standard deviation. The results highlight the importance of the EAI and SMAI as key indicators for the estimation and early estimation (respectively) of cereal yield.


  • Open Access

    Multi-Year Cereal Crop Classification Model in a Semi-Arid Region Using Sentinel-2 and Landsat 7–8 Data

    by Manel Khlif, Maria José Escorihuela, Aicha Chahbi Bellakanji, Giovanni Paolini, Zeineb Kassouk, Zohra Lili Chabaane

    This study developed a multi-year classification model for winter cereal in a semi-arid region, the Kairouan area (Tunisia). A random forest classification model was constructed using Sentinel 2 (S2) vegetation indices for a reference agricultural season, 2020/2021. This model was then applied using S2 and Landsat (7 and 8) data for previous seasons from 2011 to 2022 and validated using field observation data. The reference classification model achieved an overall accuracy (OA) of 89.3%. Using S2 data resulted in higher overall classification accuracy. Cereal classification exhibited excellent precision ranging from 85.8% to 95.1% when utilizing S2 data, while lower accuracy (41% to 91.8%) was obtained when using only Landsat data. A slight confusion between cereals and cereals growing with olive trees was observed. A second objective was to map cereals as early as possible in the agricultural season. An early cereal classification model demonstrated accurate results in February (four months before harvest), with a precision of 95.2% and an OA of 87.7%. When applied to the entire period, February cereal classification exhibited a precision ranging from 85.1% to 94.2% when utilizing S2 data, while lower accuracy (42.6% to 95.4%) was observed in general with Landsat data. This methodology could be adopted in other cereal regions with similar climates to produce very useful information for the planner, leading to a reduction in fieldwork.


  • Open Access

    Automatization of an early cereal maps classification model from 2010/2011 to 2021/2022 in a semi-arid region

    by Manel Khlif, Maria José Escorihuela, Aicha Chahbi Bellakanji, Giovanni Paolini, Zeineb Kassouk, Zohra Lili Chabaane

    Cereals represent an essential factor in the economy and food security, especially for countries that are not self-sufficient and depend on imports like Tunisia. Obtaining an early cereal map without the need to collect field data and without waiting for the end of the agriculture season helps the government to make early decisions. Hence, the first objective of our study is the development of an automatic classification model first calibrated for one agricultural year, 2020/2021 (2021), and then validated over the years 2011 through 2022 in the Kairouan governorate. The second objective is the development of a forecasting model in order to have early cereal maps several months before the harvest which occurs in June. Using Sentinel 2 and Landsat 5-7-8 data, different vegetation indices percentiles have been calculated. In order to select the best indices for cereal classification, a feature importance study over all the indexes was performed using the random forest classification algorithm reference year classification. A land cover classification model was validated for the reference year 2021, with an overall accuracy of 89.3%. This classifier has been used to elaborate land cover classification maps since 2011, focusing mainly on cereal crops. Using Sentinel 2 data, a good precision (P) for cereal crops was found, between 85,8% and 95,1%. Good to moderate accuracies were obtained when using Landsat data, between 41% and 91,8%. Then, a land cover forecasting model was validated for 11 years for different forecasting periods where we found excellent results four months before harvest (in February). We were able to obtain the cereal crop maps with a P between 85,1% and 95,1% using Sentinel 2 data and between 42,6% and 95,4% using Landsat data from four months before harvest. However, confusion between cereals and cereals grown with arboriculture was found which is due to the similarity between these two classes.With this automatic land cover model, we have been able to produce the cereal maps of the last 12 agricultural years. This approach could be also used in the future to obtain a cereal map as early as February.

  • Open Access

    Hydrological drought monitoring in the Ebro basin: Standardized Soil Moisture Index

    by Guillem Sánchez Alcalde, Maria José Escorihuela, Giovanni Paolini

    Recent studies manifest that the frequency and severity of droughts are increasing due to climate change. Drought stands as a major climate risk; thus, its understanding and study are of utter importance. Such phenomenon results from complex interactions between the atmosphere, the continental surface and water resources management, and it can lead to large socioeconomic impacts.Following the work of Wilhite and Glantz, droughts can be categorized based on their severity as: meteorological, agricultural, hydrological, and socioeconomic (Wilhite, D.A.; and M.H. Glantz, 1985). The first three approaches are described by the physical impact of the drought, while the latter deals with drought in terms of supply and demand (e.g., the lack of energy, food or drinking water).Meteorological drought is associated with a precipitation deficiency period, which can also be accompanied by high temperatures or low relative humidity. If such a period persisted in time, we would start observing a deficiency in soil moisture, and a reduction in crop population and yield. Such circumstances would indicate that we are under the influence of an agricultural drought, with the potential to evolve into a hydrological drought with time. The frequency and severity of hydrological drought are defined typically on a river basin scale, with an impact on the surface and subsurface water supply (i.e., reduced streamflow or inflow to reservoirs, lakes and ponds).Due to the effects and frequency of droughts, monitoring them is of sheer importance. Different indices have been developed for the study of droughts, based on variables such as precipitation or vegetation status. One of the most used indices is the standardized precipitation index (SPI), which shows the deviation from average precipitation. Hence, it is related to drought hazards. Each index provides different information about the drought; therefore, a combination of indices is required to identify and assess them.Drought indices can also be obtained from L-band (21 cm, 1.4 GHz) radiometers, which provide soil moisture data, among other variables. Soil moisture plays a key role in agricultural monitoring and drought forecasting. While vegetation-based drought indices can only be applied once the drought is already causing vegetation damage, soil moisture observations can forewarn of impending drought conditions.The main drawback of precipitation-based drought indices is that they require in-situ data, providing a discrete image of the drought. Despite precipitation indices based on theoretical models providing a continuum picture of the drought, their performance and reliability should be taken with a grain of salt. On the other side, soil moisture data not only does not depend on any model but also displays a continuum image of the drought.In this presentation, we will study the performance of a variety of drought indicators based on precipitation and soil moisture data in the Ebro basin region and show how they manifest hydrological drought. Namely, we have developed the standardized soil moisture index (SSI). The SSI is based on the SPI method, and we have tested this index for different integration times.