Conference Agenda

Climate change is a challenge for all sectors, but especially for agriculture. Rising temperatures in Africa negatively affect agricultural production. In addition, the demand for food is increasing, making it necessary to develop variables that describe agriculture, such as yield forecasts or phenology development stages of the different varieties cultivated. Remote sensing provides spatial and temporal continuous information that allow us to accurately assess the evolution of a particular field. In this study, we use Sentinel-2 optical data to analyse rice and wheat seasons between 2016-2022 in the Gharbia governorate (Egypt) where ground data were collected by the University of Tanta. We applied a yield model for each crop type trained in Spain and study their transferability to this region. In the case of wheat, we also test a second model that aggregates SAR data from Sentinel-1, thus evaluating the fusion of both products. We also studied the integration of the accumulated Growing Degree Days (GDDaccum), since the seasons do not start on the same dates and depending on the temperature accumulation the crops phenology evolves differently. Using the GDDaccum, the models show a better performance that when considering the timeseries evolution against the dates. The optical models provide a RMSE of about 1 T/ha for rice and 0,9 T/ha for wheat. The optical + SAR model manages to reduce the wheat model error to 0,7 T/ha. We also developed a crop type mask to evaluate the yield models performance at governorate level. Preliminary results show a RMSE of 2 T/ha for rice and wheat.

Climate change is threatening food security. To ensure food security, we do not only have to safeguard agricultural production but also optimally distribute the yields between regions. For that, decision-makers need reliable crop yield forecasts so that they can plan which regions are likely to experience crop yield losses and which regions will produce a surplus. Earth observation and machine learning are key tools to calculate such forecasts. Especially Sentinel-1 and 2 data has been used a lot as it provides regular high-resolution information about the state of crops and soil moisture. However, crop yield forecasts based on machine learning are strongly limited by the availability of field-level crop yield data, which farmers often do not like to share publicly. In this study, we evaluated if a model trained with data from a certain region can be applied elsewhere, to use training data more efficiently. Our field-level crop yield forecasts were trained using crop yield data from a farm (846 fields) in the Czech Republic for winter wheat. It was based on Sentinel-1 and 2 data and the machine learning model Extreme Gradient Boosting. The model was then tested for various farms with increasing geographical distance. The baseline was a forecast for fields of the same farm, that were not used for training. Next, the model was applied to another farm in Czechia, one in Ukraine and one in the Netherlands. The model transferability worked well for the other farm in Czechia (R²=0.64 between the forecast 1 month before harvest and observed yield). However, the model performed poorly further away than that (R²<0.13). This was related to very different weather conditions. Adding meteorological predictors or applying the model to more similar areas may help in the future to improve the transferability of the forecasts.

In this work we develop a model to forecast wheat yield at field level from Sentinel-1 (S1) and Sentinel-2 (S2) data. To do this, we calibrate the model with precise yield data acquired between 2018 and 2022 in different fields located in an agricultural region (mostly cereals) in the province of Valladolid and we validate it with data acquired across different provinces of across Spain. To minimize the temporal variability that each season and region may present, we normalized the signal from the two satellites based on the plant temperature accumulation (accumulation of Growing Degree Days, GDD_acum) based on the ERA5 air temperature product. Additionally, we test different Start-Of-Season inputs to start the GDD accumulation: a) the average planting date, b) the WorldCereal crop calendars, or c) Land Surface Phenology (LSP) metrics based on MODIS daily data. Finally, we calibrate the yield model based on a two-parameter linear regression for each GDD_acumrange considering three possible combinations: (1) using only optical parameters of S2, (2) using only microwave parameters from S1, or (3) using one parameter from S2 and one parameter from S1. The calibration results show that with S2 the yield can be estimated with errors of 800 kg/ha around 1400 ºC, S1 provides errors of 1000 kg/ha around 1700 ºC and the integration of S1 and S2 provides the lowest errors of 700 kg/ha around 1400 ºC. We tested the transferability of the model across the major wheat producing Autonomous Communities in Spain (Castilla y Leon, Castilla La Mancha, Aragon, Andalucia and Cataluña). The results show consistent results with the calibration data with minimum seasonal errors ranging from the lowest of 700 kg/ha in Andalucia to the largest 1200 kg/ha in Aragon.

The escalating frequency and intensity of climate shocks underscore the critical necessity of timely and precise data on agricultural conditions to inform responses. This data is often absent in countries where rainfed, low-input and smallholder farming systems are ubiquitous, conditions that heighten vulnerabilities to climate risks. Earth observation (EO) data can fill these gaps and support in-season agricultural monitoring, providing frequent and transparent information to guide government interventions. In smallholder agricultural systems however, there is a need to validate EO data, and build confidence in new data sources. FAO and NASA Harvest collaborated to bridge data and analytical gaps in Malawi and Namibia, binding EO applications, digital tools and field-level assessments to foster an integrated approach to agricultural monitoring. The collaboration focused on three areas: 1) mobile-based tools for the collection in situ data; 2) cropland mapping of small-holder agricultural systems; and 3) yield forecasts based on earth observation data. The creation of a suite of mobile-based survey tools to collect ground truth data was a critical element of this work, with the primary intention to provide actionable information to governments, but with secondary benefits of building an extensive validation and training data set for yield forecast and cropland mapping models. The tools built off existing developments from ArcGIS Survey123, adding new components that sped-up and lowered costs of collecting field level data, including field boundaries and yield estimates, whilst importantly developing features to provide information back to the farmer; a critical aspect to foster trust with farmers. This integrated approach provided government entities with multiple sources of corroborative evidence (field level data, early yield estimates and interpretable EO analysis) to facilitate a more informed and timely response.

Since ground-based statistical methods of yield estimation are currently not available in the Ukraine due to the war, VISTA has provided the Ukrainian Ministry of Agriculture with high resolution information on expected production volumes for winter wheat, rapeseed, winter and spring barley, grain maize and sunflower, i.e. the YPSILON service, in 2022 and 2023. The crop types are classified using Sentinel-2 data. The temporal development of the leaf area is calculated for hundreds of thousands of fields and assimilated into the PROMET crop growth model. The large number of analyzed fields enables an aggregation of yield forecasts in t/ha on different administrative levels. Through combining area under cultivation and simulated yield from PROMET, forecasts can be made for the expected production volume. Coherence information from Sentinel-1 data is used for harvest detection on field level, to determine the share of the harvested area of the total cultivated area. The results for 2023 will be shown, illustrating the resilience of the Ukrainian farmers in terms of food production as well as the consequences of the front line for agricultural production.

In the current workflow as employed for these analyses, forecasts of yield and production are possible up to 6 weeks in advance. Within the Horizon Europe Project STELAR, VISTA aims at making these forecasts possible even earlier, up to 10 weeks in advance. For this, sophisticated tools for data imputation and data fusion are being developed and integrated in STELAR’s Knowledge Lake Management System. A first outlook towards these advances will be given.

The work for Ukraine presented here has been supported by co-funding from ESA’s Network of Resources under contract numbers 3a06VS and 3717ds, as well as from BayWa AG. STELAR is funded by the European Commission’s Horizon Europe program under grant agreement number 101070122.

Precise within-field estimation of cropland productivity is crucial for informed agricultural decision-making, particularly in enabling the optimization of management practices and the pre-harvest anticipation of crop yields. The current availability of high spatiotemporal resolution of optical satellite data offers the opportunity for continuous monitoring and assessment of croplands, allowing for enhanced agricultural productivity and resource utilization. This study presents a workflow for predicting within-field grain yields focusing on winter cereal crops in Switzerland (wheat, barley and triticale). NDVI and the recently introduced kernel NDVI time series were derived from Sentinel-2 data as descriptive indicators of crop status and evolution. To ensure temporal continuity, Gaussian Process Regression (GPR) was used as a curve-fitting function to reconstruct cloud-free time series throughout the growing season. The performance of various machine learning methods (GPR, Kernel Ridge Regression, and Random Forest) to forecast yield at any point in time during the season was compared. The integration of Growing Degree Days (GDD) information as the temporal spacing reference of the time series considerably improved the accuracy and consistency of in-season yield forecasting. Using data from the same year, results indicate that grain cereal yield can be reliably predicted approximately 2-2.5 months before harvest, with an RMSE of up to 0.71 t/ha and a relative RMSE of 7.60%. Although the forecasting accuracy decreases when predicting for unseen years, the results remain satisfactory (RMSE = 0.97 t/ha, relative RMSE = 11.47%). These findings showcase the potential of the proposed workflow for in-field yield monitoring and targeted interventions, potentially reducing yield losses, optimizing farmers' management planning and enhancing food availability.

.

Evapotranspiration (ET) is a critical component in the terrestrial water cycle, and it can quantify the crop water use in agricultural regions. Land surface temperature (LST) indicates the thermal status of the surface as a consequence of the land-atmosphere exchange of energy and water fluxes, thus serving as a pivotal lower boundary condition for retrieving ET in thermal-based evaporation models. ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) has been providing high spatio-temporal TIR observations (~70 m, 1-5 days) since August 2018. Taking advantage of the ECOSTRESS observations, the European ECOSTRESS Hub (EEH) funded by the European Space Agency (ESA) focuses on the water, energy, and carbon cycles in the terrestrial ecosystems. In EEH Phase 1 (2020-2022), we produced LST and instantaneous ET data between 2018 and 2021 from models with different structures and parameterization schemes over Europe and Africa. Based on the generated LST, ET from the physically based STIC model had relatively better consistency with the measurements from the eddy covariance sites across varying aridity and diverse biomes. Taking advantage of ECOSTRESS Collection 2 data, in EEH Phase 2 (2023-2025), we target at 1) analyzing the impacts of LST estimates from different algorithms on ET retrieval over different ecosystems, 2) developing a hybrid look-up table approach for estimating daily ET at any time of day, and 3) coupling ET with GPP. Map-ready time series (>5 years) of LST, daily E, and GPP are expected to be generated with public accessibility. Overall, the EEH will provide quality-assured remote sensing products for monitoring agriculture drought and facilitate the preparation for the next generation high-resolution thermal missions, including TRISHNA (CNES/ISRO), SBG (NASA), and LSTM (ESA).

The Sen4Stat open source toolbox and the Agricultural Virtual Laboratory (AVL ) are funded by ESA with the objective to support the EO agriculture community.

The ESA Sen4Stat project demonstrates validated open source tools and best practices for national agricultural statistics with Sentinel data and facilitates the EO uptake by the National Statistical Offices. The Sen4Stat toolbox processes Sentinel-1 and Sentinel-2 according to the state-of-the-art and delivers 5 types of products: 10-m optical and SAR temporal syntheses, spectral indices and biophysical variables time series, 10-m crop type maps, crop growth conditions metrics and crop yield estimations. The project is working with pilot countries such as Spain, Senegal, Pakistan, etc. to address a wide diversity of cropping systems and agricultural data collection protocols and sampling frames. The Sen4Stat toolbox is available for download and the next 18 months will be dedicated to capacity building activities for the growing community.

The AVL is designed to be an online community open science tool to share results, knowledge and resources. Agriculture scientists can access and share Earth Observation (EO) data, high-level products, in-situ data, as well as open-source code (algorithms, models, tools) to carry out scientific studies and projects. Maximizing the offer of relevant data for the agriculture science community is the first objective of AVL. As Open Science project, the AVL also aims at fostering the collaboration between scientists and the sharing of data, products, results and source code (joint publications, inter-comparison exercise, benchmarking activities, etc.).

Climate change, the Ukraine war, armed conflicts across the globe, and the recent COVID 19 pandemic, demonstrate the vulnerability of global agricultural production to external shocks, with serious repercussions for world food trade, food access and ultimately food security of millions of people around the globe. Such multi-layered acute food supply shocks are expected to increasingly disrupt agricultural markets, trade, and food security, highlighting the urgent need for appropriate, timely and transparent risk management.

An enhanced capability for monitoring, forecasting and assessing shocks to agricultural regions across the globe is critical to better inform markets, humanitarian actors, and policy makers to ultimately help safeguard lives and livelihoods. Satellite data and analysis can fill serious gaps in agricultural information during food system shocks and when ground access is disrupted. For example, our ongoing work with Ukraine’s ministry of Agrarian Policy and Food, provided satellite driven, in season assessments of Ukraine’s agricultural production in the government controlled and occupied territories where ground data is not available, helping to inform policy and trade decisions. In our experience at NASA Harvest and GEOGLAM, despite a large and growing demand for such analysis, there is a notable deficit in institutional capacity to deliver the kinds of rapid, satellite-driven assessments. Many national and international organizations use remote sensing technologies for agricultural assessments, but a dedicated, on-demand agricultural analysis facility does not exist. The need for such standing capacity has been recognized by multiple governments, UN, humanitarian organizations, and policy frameworks i.e. AMIS. In response, we are building a dedicated facility that can be activated whenever events threaten agricultural production, or information transparency. The facility’s focus is on analyzing three primary types of food system shocks: armed conflict and war; extreme weather events; and on regions with high agricultural uncertainty or low data transparency. This talk will discuss the need for such a facility and provide examples of our rapid response work and its impact.

The WorldCereal project, funded by the European Space Agency (ESA), aims to provide a comprehensive understanding of global cropped areas, irrigation practices, and the distribution of major commodity crops such as cereals. WorldCereal has developed a dynamic open-source system that generates a range of products, including temporary crop extent, seasonal maize and cereal maps, seasonal irrigation maps, seasonal active cropland maps, and confidence layers. These products are based on the analysis of Sentinel-1 and Sentinel-2 imagery at 10 m spatial resolution, complemented by Landsat 8 imagery and AgERA5 meteorological information, and are updated at seasonal intervals for each agricultural system. WorldCereal has demonstrated the feasibility of global crop mapping by producing the first global, seasonally updated crop and irrigation maps for the year 2021. WorldCereal has also released a fully open, harmonized database of in-situ reference data related to land cover, crop type, and irrigation, enabling a broad community to access and contribute to this growing resource. WorldCereal is now entering a new phase, in which the system is being integrated into OpenEO and implemented as a cloud-based processing service in the new Copernicus Data Space Ecosystem. The system will also offer more flexibility and customization options to users, allowing them to generate tailored crop type products for their regions of interest. Moreover, the WorldCereal product suite will be extended with eight new crops, and the in-situ reference database will be updated and expanded. WorldCereal will also conduct a series of regional use cases and capacity building activities to demonstrate the system’s capabilities and to boost user uptake by the broad agricultural monitoring community. WorldCereal provides a vital tool for policymakers, international organizations, and researchers to better understand local to global cropping patterns and to inform decision-making related to food security and sustainable agriculture.

The EO4EU project, funded by the European Commission, aims to revolutionize access to and utilization of Earth Observation (EO) data through the development of the EO4EU Platform. This platform, hosted at www.eo4eu.eu, integrates major EO data sources such as GEOSS, INSPIRE, Copernicus, Galileo, and DestinE, offering a suite of tools and services tailored for environmental, governmental, and business forecasting and operations in various domains including agriculture.

Key features of the EO4EU Platform include Data Analytics Visualization, Knowledge Graph-based Decision Making, an XR (extended reality) System, an AI/ML Marketplace, a Generic Machine Learning Pipeline for Semantic Annotation, Fusion Engine, and serverless Function as a Service (FaaS). These tools empower users to effortlessly discover, analyze, and visualize EO data, supported by machine learning algorithms for handling large data volumes.

The platform utilizes cloud computing infrastructure and pre-exascale high-performance computing to efficiently process EO data, while prioritizing user-friendly interfaces for intuitive data exploration, even incorporating extended reality technologies.

EO4EU introduces technical and scientific innovations such as enhanced image compression rates, reduced data volumes, custom services with minimal labeled data requirements, robust representations of EO data, and optimized data fusion in HPC and GPU environments. Moreover, the project emphasizes the development of customizable visualization tools, granular analytics, and responsive web interfaces to observe trends, correlations, and cause-and-effect relationships in EO data.

The poster will provide insights into the project's progress, including the adopted architecture, initial user survey findings regarding EO data access and discovery, and upcoming milestones. Early access to the platform will be offered, alongside discussions on challenges and opportunities in EO data utilization.

The Copernicus Data Space Ecosystem has revolutionized the landscape of Earth Observation (EO) data exploration, accessibility, processing, and visualization. This platform allows for efficient satellite data processing for agricultural monitoring, e.g. to address national statistics, food security, and sustainable development goals. The Copernicus Data Space Ecosystem offers a comprehensive suite of functionalities, including access to Sentinel Hub and openEO APIs, free-of-charge up to predefined quotas, with the option for expanded computing resources on a commercial basis.

Introducing an innovative approach to disseminating satellite data, the Copernicus Data Space incorporates data streaming and on-the-fly processing, substantially reducing the time required for generating higher-level EO products crucial for timely decision-making in agriculture monitoring. A distinctive feature of CDSE is the immediate availability of data, eliminating the need for ordering and waiting periods. This facilitates seamless bulk data processing and streaming via OGC services, allowing for real-time visualization and analysis. Moreover, the adoption of optimized data formats like Cloud Optimized GeoTIFF (COG) enables partial reading, crucial for parallel computing and efficient data processing.

The Copernicus Data Space Ecosystem provides access to a comprehensive range of Copernicus satellite imagery, including Sentinel-1, Sentinel-2, Sentinel-3, and Sentinel-5p, along with services and data from other satellite missions like Landsat, SMOS, and Envisat. The Copernicus Browser further enhances support by enabling advanced data visualization, encompassing 3D rendering and timelapse animations.

For agricultural monitoring applications, CDSE provides invaluable resources free-of-charge for personal, research, or commercial use. For larger-scale processing needs, platforms like CREODIAS offer access to federated cloud environments, serverless processing of EO products, and dedicated EO services.

.

The agricultural sector is the biggest and least efficient water user, accounting for around 80% of total water use in Northern Africa, which is already strongly impacted by climate change with prolonged drought periods, imposing limitation to irrigation water availability. The objective of this study was to develop a procedure for the monitoring and forecasting of anthropogenic irrigation water use for the irrigation districts of Doukkala in Morocco from 2013 to 2022.

The analysis is based on the FEST-EWB model, that computes continuously in time both soil moisture (SM) and evapotranspiration based on the energy-water balances. The model has been calibrated and validated over non-irrigated areas, against land surface temperature (LST) from downscaled Sentinel3 data at 30m and modeled evapotranspiration from MOD16, GLEAM and FAOWapor. The model has been run using as input the past meteorological forcings (ECMWF ERA5-Land) and vegetation data from Sentinel2. Then, the actual irrigation volumes have been estimated through the calibrated model implementing three different irrigation strategy: the FAO approach based on SM crop stress thresholds (Allen et al., 1998), the separate and joint assimilation of satellite LST and SM (1km SMAP-Sentinel1) to update the modeled fluxes and estimate the irrigation volumes. Overall, the results suggested that the yearly total irrigation volumes modeled with the FAO approach are quite in agreement with the observed water allocations; and similar outcomes are obtained when the joint assimilation of satellite LST and SM. Finally, the calibrated model was used to implement a seasonal forecasted optimized irrigation strategy, by implementing the FEST-EWB model with seasonal meteorological forecast (ECMWF data) and the FAO irrigation strategy to provide forecasted crop water demand and optimized irrigation water needs.

This research was developed within the ESA AFRI-SMART project EO-Africa multi-scale smart agricultural water management, in the framework of EO AFRICA activities as Natioanl Incubators.

The anticipated increase in agricultural water usage, driven by a warming climate and rising population, underscores the need for operational large-scale monitoring tools in agricultural water governance. In this context, irrigation mapping plays a crucial role in sustainable management of agricultural resources.

Remote sensing technology offers a cost-effective alternative to traditional census methods for monitoring agricultural water usage. It provides spatially exhaustive near-real-time data, enabling timely interventions and adaptive management strategies.

In the context of the ESA Sentinel for Agricultural Statistics (Sen4Stat) project, a pixel-based map of irrigated areas was generated in Spain for 2022, using Sentinel-2 image time series, as well as high-quality in-situ datasets provided by the Spanish National Statistical Office and farmers' declarations.

Specific statistical and temporal metrics were designed to highlight phenological differences between irrigated and rainfed parcels at specific dates and throughout the growing season. To account for varying phenological response to irrigation across crop types, we employed a pixel-based categorical gradient boosting model. This model classified each pixel with known crop types (information from the farmers' declarations) as rainfed or irrigated. The overall accuracy of the obtained map is 91%; this good performance is also observed for individual crop types across a range of agricultural environments, spanning from olive groves in Andalucia to intensive cereal fields like barley in Castilla y Leon, and citrus orchards lining the Mediterranean coastline.

In the Sen4Stat context, this map will be used to update the statistical survey sampling frame, but it can also be very useful to support the transition towards more sustainable agriculture. In the future, it is planned to test the potential of the developed method in other places of the world.

Irrigation is the heaviest human alteration on the natural water cycle. Satellite technology represents a unique tool for disclosing irrigation dynamics (i.e., extent, timing, and quantification) that are generally poorly documented despite their primary importance in water resources management. In this contribution, we retrace main findings obtained in the fields of irrigation mapping and quantification through remote sensing data under the ESA (European Space Agency) funded Irrigation+ and 4DMED-Hydrology projects. The achieved results consist in the development of an irrigation mapping method called TSIMAP (Temporal-Stability-derived Irrigation MAPping) and of a framework for estimating irrigation water use, i.e., the SM-based (Soil Moisture-based) inversion approach. The latter led to the development of the first satellite-derived, high-resolution irrigation water use data sets, produced over four Mediterranean basins (the Po basin in Italy, the Ebro basin in Spain, the Medjerda basin in Tunisia, and the Herault basin in France) and over the Murray-Darling basin in Australia. In a new precursor project funded by ESA, i.e., the CCI-AWU (Climate Change Initiative – Anthropogenic Water Use), the SM-based inversion approach will be implemented, together with other satellite-based-approaches, to produce long-term irrigation water use estimates to benefit climate-related studies.

Groundwater plays a pivotal role for drinking water supply, agriculture and ecosystems in general. In arid areas such as the Saq-Ram aquifer at the Arabian Peninsula, groundwater levels (GWL) are strongly declining. In these regions, the observed decline in GWL can be attributed to intensive agriculture characterized by excessive groundwater usage for irrigation purposes. In the face of climate change, agricultural irrigation demands are increasing even in dry sub-humid regions in central Europe, where they previously where they previously held minor importance. As part of the KIMoDIs project, the aim of this study is to assess the effect of agriculture on the GWL using deep learning methods, focusing specifically on the federal state of Brandenburg, which is one of Germany's driest regions.

We develop an inverse approach: The predicted GWL is decomposed into partial scale-respective signals using the discrete wavelet transform. Gradient-based feature attribution methods, such as expected gradients, are being applied on these. We infer an agricultural map of the study area using optical satellite data, such as Sentinel-2, as an input and the EuroCrops dataset as a reference. That map serves as an input to a global GWL model combined with meteorological and static parameters. After model training, the computational graph of the model is expanded by the decomposed partial signals of the predicted GWL. Based on that expansion, the gradients and, hence, the agricultural attribution to the GWL is analyzed with respect to multiple scales which shall ease algorithmic sensitivity. That attribution is to be compared to crop type specific irrigation requirements. Our approach will help both groundwater management and farmers to decide on which crops, and potentially associated irrigation practices, may lead to groundwater depletion under certain climatic conditions.

Over the past 6 years Morocco has been heavily affected by droughts, with declining rainfall resulting in limited water available in reservoirs. The challenge is to optimise the water allocation between agriculture, urban areas and tourism.

This presentation will demonstrate how we use satellite data to monitor agricultural water use from basin to field level in the Tensift Basin of Morocco. Complex geospatial data of FAO’s open-access WaPOR database together with eLEAF’s high resolution data is translated into credible, tangible information that can be directly used for reporting, decision making and planning.

eLEAF and RESING co-developed the Water Consumption Dashboard (WCD) with (1) the water board (ABHT) mandated for integrated water resources management and (2) the irrigation office (ORMVAH) managing irrigation schemes and training farmers in optimal water use. The information provided is intended to be easy-to-digest and aimed at professionals without prior GIS experience. The dashboard provides users with actual information every ten days.

Furthermore for the Haouz plain we assessed the conversion to drip irrigation in 2018. Long-term WaPOR analyses indicate a slightly decreasing trend in water consumption (ETa) of -4,2%, and increasing trends agricultural productivity (NPP +3,5%) and water productivity (WP +6,7%). The analysis does also reveal a reduction in cultivated areas. However, because of the recent high interannual fluctuations of precipitation and the stop of surface water allocation in 2021 from reservoirs and the limited series of data available after conversion, does not allow definitive results on the impact of modernization (yet).

The cooperation with ABHT and ORMVAH recently entered a two years demonstration phase to internally adapt the WCD to identify illegal groundwater withdrawals, monitoring of water consumption, crop area and development and irrigation efficiency. The developed tools contribute to more transparent, equitable and sustainable water use.

African drylands are particularly important for research and innovation because they support 75% of the continent’s agriculture; are highly vulnerable to the impacts of climate change; have high rates of food and economic insecurity that trigger humanitarian crises; are biodiversity hotspots; and play an important role in regulating the Earth's climate system via carbon storage and rainfall triggered by evapotranspiration (i.e., “rainbow water”). Researchers and advisory services increasingly leverage advanced remote sensing technology such as the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) and evapotranspiration (ET)-derived metrics like the evaporative stress index (ESI) to monitor agricultural droughts in African drylands. However, there is an opportunity to enhance the reliability of these products with the emergence of a new generation of hyperspectral remote sensing missions: Hyperspectral Precursor and Application Mission (PRISMA) and the Environmental Mapping and Analysis Program (ENMAP). In this study, we employ eddy covariance flux towers in Kapiti Ranch of Machakos County, Kenya to evaluate the performance of ECOSTRESS ET and ESI products driven by PRISMA and ENMAP like hyperspectral vegetation indices resampled from fluorescence box (FloX) ground spectra. The enhanced products are demonstrated with actual PRISMA and ENMAP imagery. Our findings reveal the superiority of hyperspectral narrowbands over thermal infrared, particularly in distinguishing transpiration and soil evaporation dynamics. Such information will feed into a potentials and limitations analysis for the upcoming Copernicus Hyperspectral Imaging Mission for the Environment (CHIME) and Land Surface Temperature Monitoring (LSTM) missions. CHIME and LSTM afford the opportunity for delivering the highest quality ET and ESI estimates consistently across Africa at frequent intervals.

.