Performance of water indices for large-scale water resources monitoring using Sentinel-2 data in Ethiopia.

Evaluating the performance of water indices and water-related ecosystems is crucial for Ethiopia. This is due to limited information on the availability and distribution of water resources at the country scale, despite its critical role in sustainable water management, biodiversity conservation, and ecosystem resilience. The objective of this study is to evaluate the performance of seven water indices and select the best-performing indices for detecting surface water at country scale. Sentinel-2 data from December 1, 2021, to November 30, 2022, were used for the evaluation and processed using the Google Earth Engine. The indices were evaluated using qualitative visual inspection and quantitative accuracy indicators of overall accuracy, producer's accuracy, and user's accuracy. Results showed that the water index (WI) and automatic water extraction index with shadow (AWEIsh) were the most accurate ones to extract surface water. For the latter, WI and AWEIsh obtained an overall accuracy of 96% and 95%, respectively. Both indices had approximately the same spatial coverage of surface water with 82,650 km2 (WI) and 86,530 km2 (AWEIsh) for the whole of Ethiopia. The results provide a valuable insight into the extent of surface water bodies, which is essential for water resource planners and decision-makers. Such data can also play a role in monitoring the country's reservoirs, which are important for the country's energy and economic development. These results suggest that by applying the best-performing indices, better monitoring and management of water resources would be possible to achieve the Sustainable Development Goal 6 at the regional level.

A machine learning approach for modeling the occurrence of the major intermediate hosts for schistosomiasis in East Africa.

Schistosomiasis, a prevalent water-borne disease second only to malaria, significantly impacts impoverished rural communities, primarily in Sub-Saharan Africa where over 90% of the severely affected population resides. The disease, majorly caused by Schistosoma mansoni and S. haematobium parasites, relies on freshwater snails, specifically Biomphalaria and Bulinus species, as crucial intermediate host (IH) snails. Targeted snail control is advisable, however, there is still limited knowledge about the community structure of the two genera especially in East Africa. Utilizing a machine learning approach, we employed random forest to identify key features influencing the distribution of both IH snails in this region. Our results reveal geography and climate as primary factors for Biomphalaria, while Bulinus occurrence is additionally influenced by soil clay content and nitrogen concentration. Favorable climate conditions indicate a high prevalence of IHs in East Africa, while the intricate connection with geography might signify either dispersal limitations or environmental filtering. Predicted probabilities demonstrate non-linear patterns, with Bulinus being more likely to occur than Biomphalaria in the region. This study provides foundational framework insights for targeted schistosomiasis prevention and control strategies in the region, assisting health workers and policymakers in their efforts.

The Fragile State of Industrial Agriculture: Estimating Crop Yield Reductions in a Global Catastrophic Infrastructure Loss Scenario.

Modern civilization relies on a complex, globally interconnected industrial agriculture system to produce food. Its unprecedented yields hinge on external inputs like machinery, fertilizers, and pesticides, rendering it vulnerable to disruptions in production and international trade. Such a disruption could be caused by large-scale damage to the electrical grid. Solar storms, nuclear detonations in the upper atmosphere, pandemics, or cyber-attacks, could cause this severe damage to electrical infrastructure. To assess the impact of such a global catastrophic infrastructure loss on major food crops (corn, rice, soybean, wheat), we employ a generalized linear model. The predictions show a crop-specific yield reduction between 15% and 37% in phase 1, the year after the catastrophe, assuming rationed use of fertilizers, pesticides, and fuel stocks. In phase 2, when all stocks are depleted, yields decrease by 35%-48%. Soybean is less affected in phase 1, while all crops experience strong declines in phase 2. Europe, North and South America, and parts of India, China, and Indonesia face major yield reductions, potentially up to 75%, while most African countries are less affected. These findings underscore the necessity for preparation by highlighting the vulnerability of the food system.

Exploring the interplay between climate change and schistosomiasis transmission dynamics.

Schistosomiasis, a neglected tropical disease caused by parasitic worms, poses a major public health challenge in economically disadvantaged regions, especially in Sub-Saharan Africa. Climate factors, such as temperature and rainfall patterns, play a crucial role in the transmission dynamics of the disease. This study presents a deterministic model that aims to evaluate the temporal and seasonal transmission dynamics of schistosomiasis by examining the influence of temperature and rainfall over time. Equilibrium states are examined to ascertain their existence and stability employing the center manifold theory, while the basic reproduction number is calculated using the next-generation technique. To validate the model's applicability, demographic and climatological data from Uganda, Kenya, and Tanzania, which are endemic East African countries situated in the tropical region, are utilized as a case study region. The findings of this study provide evidence that the transmission of schistosomiasis in human populations is significantly influenced by seasonal and monthly variations, with incidence rates varying across countries depending on the frequency of temperature and rainfall. Consequently, the region is marked by both schistosomiasis emergencies and re-emergences. Specifically, it is observed that monthly mean temperatures within the range of 22-27 °C create favorable conditions for the development of schistosomiasis and have a positive impact on the reproduction numbers. On the other hand, monthly maximum temperatures ranging from 27 to 33 °C have an adverse effect on transmission. Furthermore, through sensitivity analysis, it is projected that by the year 2050, factors such as the recruitment rate of snails, the presence of parasite egg-containing stools, and the rate of miracidia shedding per parasite egg will contribute significantly to the occurrence and control of schistosomiasis infections. This study highlights the significant influence of seasonal and monthly variations, driven by temperature and rainfall patterns, on the transmission dynamics of schistosomiasis. These findings underscore the importance of considering climate factors in the control and prevention strategies of schistosomiasis. Additionally, the projected impact of various factors on schistosomiasis infections by 2050 emphasizes the need for proactive measures to mitigate the disease's impact on vulnerable populations. Overall, this research provides valuable insights to anticipate future challenges and devise adaptive measures to address schistosomiasis transmission patterns.

Application of multiple stable isotopes to aid identification of the origin of regional and organic animal products in Hesse, Germany.

There is an increasing global demand for regional and organic produce. However, the growth of these markets depends on consumers' trust. Thus, novel methods must be developed to aid the verification of the origin of produce. We built on our previous study to identify the geographical origin and production method of animal-derived food products. Thirty-samples of eggs, 99 of milk, 34 of beef, and 62 of pork were collected from different regions in central Germany and analysed for their stable isotopic composition. The analysis followed a single-variate authentification approach using five isotope signatures, δ18O, δ2H, δ13C, δ15N, and δ34S. The best-performing indicators for verification of the geographical origin were δ15N and δ34S for beef; δ18O, δ2H, and δ13C for milk, and δ2H and δ13C for pork. These tracers indicated statistically significant differences among regions with the exception of pork; the results recorded for eggs were inconclusive. It was possible to distinguish between production methods by means of δ15N and δ34S (beef); all five tracers (eggs), and δ13C, δ15N, and δ34S (milk). This study demonstrated how the analysis of stable isotopes can be employed to determine the geographic region of origin and production method of animal-derived products in Germany.

Climate change adaptation strategies for sustainable water management in the Indus basin of Pakistan.

Pakistan's agriculture faces water security challenges owing to insecure water supply and bad governance. The increasing food demand of the growing population and climate change vulnerability are future key threats to water sustainability. In this study, the current and future water demands as well as management strategies are evaluated for two climate change Representative Concentration Pathways (RCP2.6 and RCP8.5) for the Punjab and Sindh provinces in the Indus basin of Pakistan. The RCPs are assessed for the regional climate model REMO2015, which was found to be the best-fitting model for the current situation in a preceding model comparison using Taylor diagrams. The status quo water consumption (CWRarea) is estimated to 184 km3 yr-1, consisting of 76 % blue water (freshwater from surface water and groundwater), 16 % green water (precipitation), and 8 % grey water (required to leach out the salts from the root zone). The results of the future CWRarea indicates that RCP2.6 is more vulnerable than RCP8.5 in view of water consumption as the vegetation period of crops is reduced under RCP8.5. For both pathways (RCP2.6 and RCP8.5), CWRarea increases gradually in the midterm (2031-2070) and becomes extreme at the end of the long term (2061-2090). The future CWRarea increases up to +73 % under the RCP2.6 and up to +68 % in the RCP8.5 compared to the status quo. However, the increase in CWRarea could be restrained up to -3 % compared to the status quo through the adaptation of alternative cropping patterns. The results further show that the future CWRarea under climate change could be even decreased by up to -19 % through the collective implementation of improved irrigation technologies and optimized cropping patterns.

Accuracy assessment of inverse distance weighting interpolation of groundwater nitrate concentrations in Bavaria (Germany).

For the designation of nitrate vulnerable zones under the EU Nitrate Directive, some German federal states use inverse distance weighting (IDW) as interpolation method. Our study quantifies the accuracy of IDW with respect to the designation of areas with a groundwater nitrate concentration above the threshold of 50 mg NO3/l using a dataset of 5790 groundwater monitoring sites in Bavaria. The results show that the absolute differences of nitrate concentrations between the monitoring sites are only weakly correlated within a range of no more than 0.4 km. The IDW cross-validated nitrate concentration of measurement sites shows a mean absolute error of 7.0 mg NO3/l and the number of measurement sites above 50 mg NO3/l is 44% too low by interpolation for all sites as a whole. The corresponding values for interpolation separately for the 18 hydrogeological regions in Bavaria are 7.1 mg NO3/l and 38%. The sensitivity and the accuracy of nitrate concentration maps due to the variation of IDW parameters and the position of sampling points are analysed by Monte Carlo IDW interpolations using a Random Forest modelled map as reference spatial distribution. Compared to this reference map, the area with a concentration above 50 mg NO3/l in groundwater is estimated by IDW to be 46% too low for the best IDW parametrization. Overall, IDW interpolation systematically underrates the occurrence of higher range nitrate concentrations. In view of these underestimations, IDW does not appear to be a suitable regionalization method for the designation of nitrate vulnerable zones, neither when applied for a federal state as a whole nor when interpolated separately for hydrogeological regions.

Perennial biomass cropping and use: Shaping the policy ecosystem in European countries.

Demand for sustainably produced biomass is expected to increase with the need to provide renewable commodities, improve resource security and reduce greenhouse gas emissions in line with COP26 commitments. Studies have demonstrated additional environmental benefits of using perennial biomass crops (PBCs), when produced appropriately, as a feedstock for the growing bioeconomy, including utilisation for bioenergy (with or without carbon capture and storage). PBCs can potentially contribute to Common Agricultural Policy (CAP) (2023-27) objectives provided they are carefully integrated into farming systems and landscapes. Despite significant research and development (R&D) investment over decades in herbaceous and coppiced woody PBCs, deployment has largely stagnated due to social, economic and policy uncertainties. This paper identifies the challenges in creating policies that are acceptable to all actors. Development will need to be informed by measurement, reporting and verification (MRV) of greenhouse gas emissions reductions and other environmental, economic and social metrics. It discusses interlinked issues that must be considered in the expansion of PBC production: (i) available land; (ii) yield potential; (iii) integration into farming systems; (iv) R&D requirements; (v) utilisation options; and (vi) market systems and the socio-economic environment. It makes policy recommendations that would enable greater PBC deployment: (1) incentivise farmers and land managers through specific policy measures, including carbon pricing, to allocate their less productive and less profitable land for uses which deliver demonstrable greenhouse gas reductions; (2) enable greenhouse gas mitigation markets to develop and offer secure contracts for commercial developers of verifiable low-carbon bioenergy and bioproducts; (3) support innovation in biomass utilisation value chains; and (4) continue long-term, strategic R&D and education for positive environmental, economic and social sustainability impacts.

Urbanisation process generates more independently-acting stressors and ecosystem functioning impairment in tropical Andean streams.

The tropical Andes are experiencing rapid population growth and urbanisation has become a major driver impairing stream ecosystems. However, knowledge about multiple-stressors effects on urbanised Andean streams is lacking. In southern Ecuador, we assessed how multiple stressors determine the structural (aquatic invertebrate metrics) and functional (organic matter breakdown and delta N of primary consumers) attributes of streams in a densely populated watershed without wastewater treatment and with contrasting land uses. We found that urbanised streams exhibited individual-stressor effects and that stressor interactions were rare. While structural and function attributes responded negatively to urbanisation, ecosystem functioning metrics were influenced most. Stream ecosystem functions were influenced by water-chemistry stressors, whereas aquatic invertebrate metrics were influenced by physical-habitat stressors. We suggest that managers of urbanised streams in the Andes immediately focus on the most important stressors by reducing inputs of inorganic N and P, re-establishing stream flow and substrate heterogeneity, and restoring riparian vegetation instead of attempting to elucidate intricate interactions among stressors. Our result also demonstrate that stream biomonitoring programs would benefit from a combination of structural and functional indicators to assess anthropogenic effects in a multiple-stressors scenario.

Economic and environmental impact assessment of sustainable future irrigation practices in the Indus Basin of Pakistan.

Pakistan's agriculture is characterized by insecure water supply and poor irrigation practices. We investigate the economic and environmental feasibility of alternative improved irrigation technologies (IIT) by estimating the site-specific irrigation costs, groundwater anomalies, and CO2 emissions. IIT consider different energy sources including solar power in combination with changes in the irrigation method. The status quo irrigation costs are estimated to 1301 million US$ year-1, its groundwater depletion to 6.3 mm year-1 and CO2 emissions to 4.12 million t year-1, of which 96% originate from energy consumption and 4% via bicarbonate extraction from groundwater. Irrigation costs of IIT increase with all energy sources compared to the status quo, which is mainly based on diesel engine. This is because of additional variable and fixed costs for system's operation. Of these, subsidized electricity induces lowest costs for farmers with 63% extra costs followed by solar energy with 77%. However, groundwater depletion can even be reversed with 35% rise in groundwater levels via IIT. Solar powered irrigation can break down CO2 emissions by 81% whilst other energy sources boost emissions by up to 410%. Results suggest that there is an extremely opposing development between economic and ecological preferences, requiring stakeholders to negotiate viable trade-offs.

Assessment of multiple stable isotopes for tracking regional and organic authenticity of plant products in Hesse, Germany.

As demand for regional and organically produced foodstuff has increased in Europe, the need has arisen to verify the products' origin and production method. For food authenticity tracking (production method and origin), we examined 286 samples of wheat (Triticum aestivum), potatoes (Solanum tuberosum), and apples (Malus domestica) from different regions in Germany for their stable isotope compositions of oxygen, hydrogen, carbon, nitrogen and sulphur. Single-variate authentication methods were used. Suitable isotope tracers to determine wheat's regional origin were δ18O and δ34S. δ13C helped to distinguish between organic and conventional wheat samples. For the separation of the production regions of potatoes, several isotope tracers were suitable (e.g. δ18O, δ2H, δ15N, δ13C and δ34S isotopes in potato protein), but only protein δ15N was suitable to differentiate between organic and conventional potato samples. For the apple samples, 2H and 18O isotopes helped to identify production regions, but no significant statistical differences could be found between organically and conventionally farmed apples. For food authenticity tracking, our study showed the need to take the various isotopes into account. There is an urgent need for a broad reference database if isotope measurements are to become a main tool for determining product's origin.

A research framework for projecting ecosystem change in highly diverse tropical mountain ecosystems.

Tropical mountain ecosystems are threatened by climate and land-use changes. Their diversity and complexity make projections how they respond to environmental changes challenging. A suitable way are trait-based approaches, by distinguishing between response traits that determine the resistance of species to environmental changes and effect traits that are relevant for species' interactions, biotic processes, and ecosystem functions. The combination of those approaches with land surface models (LSM) linking the functional community composition to ecosystem functions provides new ways to project the response of ecosystems to environmental changes. With the interdisciplinary project RESPECT, we propose a research framework that uses a trait-based response-effect-framework (REF) to quantify relationships between abiotic conditions, the diversity of functional traits in communities, and associated biotic processes, informing a biodiversity-LSM. We apply the framework to a megadiverse tropical mountain forest. We use a plot design along an elevation and a land-use gradient to collect data on abiotic drivers, functional traits, and biotic processes. We integrate these data to build the biodiversity-LSM and illustrate how to test the model. REF results show that aboveground biomass production is not directly related to changing climatic conditions, but indirectly through associated changes in functional traits. Herbivory is directly related to changing abiotic conditions. The biodiversity-LSM informed by local functional trait and soil data improved the simulation of biomass production substantially. We conclude that local data, also derived from previous projects (platform Ecuador), are key elements of the research framework. We specify essential datasets to apply this framework to other mountain ecosystems.

Agricultural land is the main source of stream sediments after conversion of an African montane forest.

In many parts of Africa, soil erosion is an important problem, which is evident from high sediment yields in tropical montane streams. Previous studies in Kenya pointed to a large contribution from catchments cultivated by smallholder farmers. This led to the hypothesis that unpaved tracks and gullies are the main sediment sources in smallholder agriculture catchments of the highlands of Kenya. The aim of this study was to investigate the sediment sources with sediment fingerprinting to generate the knowledge base to improve land management and to reduce sediment yields. Four main sediment sources (agricultural land, unpaved tracks, gullies and channel banks) and suspended sediments were analysed for biogeochemical elements as potential tracers. To apportion the catchments target sediment to different sources, we applied the MixSIAR un-mixing modelling under a Bayesian framework. Surprisingly, the fingerprinting analysis showed that agricultural land accounted for 75% (95% confidence interval 63-86%) of the total sediment. Channel banks contributed 21% (8-32%), while the smallest contributions to sediment were generated by the unpaved tracks and gullies with 3% (0-12%) and 1% (0-4%), respectively. Erosion management strategies should target agricultural lands with an emphasis on disconnecting unpaved tracks form hillslope source areas to reduce sediment yields to Lake Victoria.

Diurnal Patterns in Solute Concentrations Measured with In Situ UV-Vis Sensors: Natural Fluctuations or Artefacts?

In situ spectrophotometers measuring in the UV-visible spectrum are increasingly used to collect high-resolution data on stream water quality. This provides the opportunity to investigate short-term solute dynamics, including diurnal cycling. This study reports unusual changes in diurnal patterns observed when such sensors were deployed in four tropical headwater streams in Kenya. The analysis of a 5-year dataset revealed sensor-specific diurnal patterns in nitrate and dissolved organic carbon concentrations and different patterns measured by different sensors when installed at the same site. To verify these patterns, a second mobile sensor was installed at three sites for more than 3 weeks. Agreement between the measurements performed by these sensors was higher for dissolved organic carbon (r > 0.98) than for nitrate (r = 0.43-0.81) at all sites. Higher concentrations and larger amplitudes generally led to higher agreement between patterns measured by the two sensors. However, changing the position or level of shading of the mobile sensor resulted in inconsistent changes in the patterns. The results of this study show that diurnal patterns measured with UV-Vis spectrophotometers should be interpreted with caution. Further work is required to understand how these measurements are influenced by environmental conditions and sensor-specific properties.

Changing climate - Changing livelihood: Smallholder's perceptions and adaption strategies.

Experts expect that climate change will soon have a severe impact on the lives of farmers in the region surrounding Kerala, India. This region, which is known for its monsoon climate (which involves a distinct temporal and spatial variation in rainfall), has experienced a decrease in annual rainfall over the last century. This study is aimed at investigating how smallholder farmers perceive climate change and at identifying the methods that these smallholders use to adapt to climate change. We use data collected from a survey of 215 households to compare the climate vulnerability of three watershed communities in Kerala. We find that the farmers perceive substantial increases in both temperature and the unpredictability of monsoons; this is in accordance with actual observed weather trends. The selection of effective adaptation strategies is one of the key challenges that smallholders face as they seek to reduce their vulnerability. The surveyed households simultaneously use various adaptation methods, including information and communication technology, crop and farm diversification, social networking through cooperatives, and soil and water conservation measures. The results of a binary regression model reveal that the household head's age, education and gender, as well as the farm's size and the household's size, assets, livestock ownership, poverty status and use of extension services, are all significantly correlated with the households' choices regarding adaptations to cope with climate change.

Accounting for multiple ecosystem services in a simulation of land-use decisions: Does it reduce tropical deforestation?

Conversion of tropical forests is among the primary causes of global environmental change. The loss of their important environmental services has prompted calls to integrate ecosystem services (ES) in addition to socio-economic objectives in decision-making. To test the effect of accounting for both ES and socio-economic objectives in land-use decisions, we develop a new dynamic approach to model deforestation scenarios for tropical mountain forests. We integrate multi-objective optimization of land allocation with an innovative approach to consider uncertainty spaces for each objective. These uncertainty spaces account for potential variability among decision-makers, who may have different expectations about the future. When optimizing only socio-economic objectives, the model continues the past trend in deforestation (1975-2015) in the projected land-use allocation (2015-2070). Based on indicators for biomass production, carbon storage, climate and water regulation, and soil quality, we show that considering multiple ES in addition to the socio-economic objectives has heterogeneous effects on land-use allocation. It saves some natural forest if the natural forest share is below 38%, and can stop deforestation once the natural forest share drops below 10%. For landscapes with high shares of forest (38%-80% in our study), accounting for multiple ES under high uncertainty of their indicators may, however, accelerate deforestation. For such multifunctional landscapes, two main effects prevail: (a) accelerated expansion of diversified non-natural areas to elevate the levels of the indicators and (b) increased landscape diversification to maintain multiple ES, reducing the proportion of natural forest. Only when accounting for vascular plant species richness as an explicit objective in the optimization, deforestation was consistently reduced. Aiming for multifunctional landscapes may therefore conflict with the aim of reducing deforestation, which we can quantify here for the first time. Our findings are relevant for identifying types of landscapes where this conflict may arise and to better align respective policies.

Trade-offs between parameter constraints and model realism: a case study.

Tightly constraint parameter ranges are seen as an important goal in constructing hydrological models, a difficult task in complex models. However, many studies show that complex models are often good at capturing the behaviour of a river. Therefore, this study explores the trade-offs between tightly constrained parameters and the ability to predict hydrological signatures, that capture the behaviour of a river. To accomplish this we built five models of differing complexity, ranging from a simple lumped model to a semi-lumped model with eight spatial subdivisions. All models are built within the same modelling framework, use the same data, and are calibrated with the same algorithm. We also consider two different methods for the potential evapotranspiration. We found that that there is a clear trade-off along the axis of complexity. While the more simple models can constrain their parameters quite well, they fail to get the hydrological signatures right. It is the other way around for the more complex models. The method of evapotranspiration only influences the parameters directly related to it. This study highlights that it is important to focus not only on parametric uncertainty. Tightly constrained parameters can be misguiding as they give credibility to oversimplified model structures.

Response of maize biomass and soil water fluxes on elevated CO2 and drought-From field experiments to process-based simulations.

The rising concentration of atmospheric carbon dioxide (CO2 ) is known to increase the total aboveground biomass of several C3 crops, whereas C4 crops are reported to be hardly affected when water supply is sufficient. However, a free-air carbon enrichment (FACE) experiment in Braunschweig, Germany, in 2007 and 2008 resulted in a 25% increased biomass of the C4 crop maize under restricted water conditions and elevated CO2 (550 ppm). To project future yields of maize under climate change, an accurate representation of the effects of eCO2 and drought on biomass and soil water conditions is essential. Current crop growth models reveal limitations in simulations of maize biomass under eCO2 and limited water supply. We use the coupled process-based hydrological-plant growth model Catchment Modeling Framework-Plant growth Modeling Framework to overcome this limitation. We apply the coupled model to the maize-based FACE experiment in Braunschweig that provides robust data for the investigation of combined CO2 and drought effects. We approve hypothesis I that CO2 enrichment has a small direct-fertilizing effect with regard to the total aboveground biomass of maize and hypothesis II that CO2 enrichment decreases water stress and leads to higher yields of maize under restricted water conditions. Hypothesis III could partly be approved showing that CO2 enrichment decreases the transpiration of maize, but does not raise soil moisture, while increasing evaporation. We emphasize the importance of plant-specific CO2 response factors derived by use of comprehensive FACE data. By now, only one FACE experiment on maize is accomplished applying different water levels. For the rigorous testing of plant growth models and their applicability in climate change studies, we call for datasets that go beyond single criteria (only yield response) and single effects (only elevated CO2 ).

Large scale prediction of groundwater nitrate concentrations from spatial data using machine learning.

Reducing nitrogen inputs, in particular nitrate, to groundwater is becoming increasingly important to fulfil requirements of the European Water Framework Directive. When developing management plans for mitigation measures at larger scales, complex hydro-biogeochemical models reach their limits due to data availability and spatial discretization. To circumvent this problem, the spatial distribution of nitrate concentration in groundwater is estimated using a parsimonious GIS-based statistical approach. Point nitrate concentrations and spatial environmental data as predictors are used to train statistical models. In order to compile the spatial predictors with the respective monitoring sites, different designs of contributing areas (buffer zones) and their effects on the performance of different statistical models are investigated. Multiple Linear Regression (MLR), Classification and Regression Trees (CART), Random Forest (RF) and Boosted Regression Trees (BRT) are compared in terms of the predictive performance of each model according to various objective functions. We determine the most influential spatial predictors used in the respective models. After training the models with a subset of the data, we then predict the spatial nitrate distribution in groundwater for the entire federal state of Hesse, Germany on a 1 × 1 km grid by only the spatial environmental data. The Random Forest model outperforms the other models (R2 = 0.54), relying on hydrogeological units, the percentage of arable land and the nitrogen balance as the three most influencing predictors based on a 1000 m circular contributing area. The use of exclusively spatial available predictors is a big step forward in the prediction of nitrate in groundwater on regional scale.