Climate change is projected to exacerbate food insecurity in sub-Saharan Africa (SSA) by reducing crop yields and soil fertility. Many climate change impact studies in SSA have overlooked long-term effects of soil fertility on crop yield. We evaluated maize yields under different scenarios of soil fertility (using soil organic carbon as a proxy) and climate change (considering changes in temperature, rainfall, and CO2) at four sites in SSA. Using an ensemble of 15 calibrated soil-crop models, we found a strong consensus that, without fertilization, soil fertility declines over time, impacting maize yields more strongly than changes in temperature, rainfall, or CO2. The model ensemble indicated that when accounting for soil fertility changes, the yield benefits of combined application of organic and mineral inputs increase over time, even under climate change. These findings highlight the importance of considering long-term change in soil fertility when assessing impacts of climate change and integrated nutrient management on crop production in SSA.

Study region: Germany, with a focus on Brandenburg, where the drought after 2018 caused a strong decline in groundwater storage and increased pressure on regional water resources. Study focus: This study evaluates the performance of the Global Gravity-based Groundwater Product, G3P, derived from GRACE and GRACE FO satellite gravimetry. It also assesses a downscaling framework that converts coarse groundwater storage anomalies from 0.5 degrees to 1 km resolution. Two modelling approaches, Multiscale Geographically Weighted Regression (MGWR) and Random Forest (RF), were used with high-resolution hydroclimatic and land surface variables as predictors. Model performance was validated against in situ observations. Additionally, temporal trends (2002-2020) and seasonal dynamics were analysed to assess long-term groundwater changes. New hydrological insights for the region: Results show that RF achieved higher predictive accuracy and better spatial representation than MGWR. The downscaled estimates improved cross correlation with in situ observations by 24.0% for RF and 21.0% for MGWR compared with the original GRACE-based groundwater storage anomalies. Trend analysis indicates a persistent decline in groundwater storage anomalies from 2002 to 2020, with stronger depletion after 2018. Seasonal analysis shows that wet season anomalies deepened from-90 mm in 2002 to-160 mm in 2020, while dry season anomalies increased from-55 mm to-178 mm. The high-resolution groundwater storage anomalies produced by the Random Forest framework provide improved spatial detail and support regional groundwater assessment and distributed hydrological modelling in Germany.

Context: Crop rotations provide agronomic benefits over monocropping, such as enhanced nitrogen supply, improved weed and pest control, and higher yields. Although the theoretical understanding of optimal rotations has advanced, little is known about their real-world implementation and the factors influencing rotation decisions on large scales. Objective: Understanding these factors is key for projecting future cropping patterns, refining agricultural policy, and improving crop models that often oversimplify rotation practices. This study identifies the drivers influencing operational crop rotations across Central Europe and projects future cropping patterns in the region. Methods: We analyse over 16 million field-year combinations from Germany, Austria, and the Czech Republic. Using a random forest algorithm, we determine feature importance and apply a novel machine learning approach that incorporates uncertainty in farmers' decision-making to provide a potential outlook on cropping patterns until 2070. Results and Conclusions: Historical cropping patterns, agronomic practices, and legume commodity prices significantly shaped crop rotations across the region. Projections indicate a substantial increase in legume cultivation over the coming decades, with implications for nitrogen budgets, dietary transitions, and in-silico upscaling. Significance: Rather than optimizing rotations, this study identifies key drivers of operational crop rotations in Central Europe. The findings provide the basis for large-scale simulations that represent cropping patterns more realistically. To the best of our knowledge, the data set compiled here is the most extensive yet analysed in the context of operational crop rotation management.

Abstract This study connects the dots between global extent of severe water scarcity (SWS) events and spikes in food price. The authors start with three staple crops (rice, wheat, and maize) using a empirical but crop specific characterization of severe water scarcity occurrence, which is defined based on the area of land cultivated with each studied crop that on a given year is under SWS conditions. Water scarcity is estimated based on 1, 3, and 12 months standardized precipitation evapotranspiration index during crop specific sensitive periods (SPs). SPs coincide with the 4 months prior to harvest. A SWS‐wheat price relationship model was developed for period 2001–2021 and tested for 1986–2000 and 2022–2024 with future projections calculated under climate change using climate model simulations from CMIP5 and CMIP6 up to 2100. The results show a marked increase in wheat prices driven by increasing SWS area, which is in turn a function of greenhouse gas emissions. The results indicate that the meanglobal mean temperature increase by 3°C (compared to 1951–1980) could lead to the tripling of the mean global wheat price compared to 2010 (after deflating).

Wet grasslands are among the most effective terrestrial ecosystems for long-term carbon storage, yet their stability can be threatened by climate change and altered groundwater regimes. This study applies the MONICA agroecosystem model enhanced through dynamic coupling with the individual-based grassland model GRASSMIND to evaluate carbon, nitrogen, and biomass dynamics in Brandenburg's wet grasslands (2021-2100) under three groundwater table scenarios and RCP 2.6, 4.5, and 8.5 climate pathways. Shallow groundwater conditions (similar to 30 cm) were associated with smaller soil organic carbon (SOC) loss (< 0.6 Mg C ha(-)& sup1; yr(-)& sup1;), suppressed nitrous oxide emissions, and limited nitrate leaching. In contrast, deep or unmanaged water tables increased aerobic decomposition and mineral nitrogen losses, especially under RCP 8.5, suggesting a critical climate-hydrology threshold around mid-century. Coupling MONICA with GRASSMIND allows species composition shifts to be represented and provides an exploratory assessment of how trait-based competition may influence biomass projections in wet grassland modelling. This study highlights that groundwater level management exerts a stronger control over ecosystem stability than climate forcing alone. These findings underscore the need for adaptive water regime strategies and model-based planning tools to safeguard the climate regulation potential of wet grasslands.

Context: The global shift toward sustainable agriculture has increased interest in using process-based models to design and optimize intercropping systems. However, these models differ fundamentally in how they represent trade-offs (competition for light, water, and nutrients) and synergies (facilitation, complementarity) in resource sharing between species. This conceptual variation creates uncertainty in model selection and application, particularly since most models were originally developed for monoculture and subsequently adapted for intercropping. Objective: In this study, we describe how current crop models represent interspecies resource-sharing mechanisms, analyse their structural differences, and synthesize findings from existing validation studies to understand how their structural differences affect model performance. The models examined include APSIM (APSIM-Canopy, APSIM-Micromet, APSIM-Strip, APSIM-Alternating, APSIM-APSwim, APSIM-SoilArbitrator), DayCent, DSSAT-Mixed, DSSAT-MPI, LandscapeDNDC, LUCIA, MONICA, SIMPLACE Lintul5-Intercrop, STICS-Big-Leaf, STICS-Multilayer, and WaNuLCAS. Methods: Through the Agricultural Model Intercomparison and Improvement Project (AgMIP) platform, we engaged with model developers and expert users to collect detailed information on how crop models represent intercropping systems using structured interviews and questionnaires. We then developed a framework that groups models by their core conceptual approaches to simulating resource sharing. Finally, we synthesize findings from existing quantitative validation studies to connect conceptual intercomparison to predictive performance across different intercrop characteristics and environments. Results and Conclusions: Our analysis identifies six distinct conceptual approaches for simulating light sharing and four for belowground resource (water and nutrient) competition. Intercrop models show greater structural divergence in canopy than in belowground representation. Furthermore, competitive trade-offs (light, water, and nutrients) are widely represented while facilitative and other complex processes like Na-fixation, plasticity (shoot and root), microclimate effects or hydraulic lift are often simplified or omitted. Our analysis of model validation studies reveals a critical trade-off: structurally complex models often perform well in simulating intercropping when calibration is done on sole crops, whereas simpler models require extensive intercrop-specific calibration to achieve better prediction performance. This distinction is vital for model application in data-scarce environments, as more complex architectures can leverage existing sole-crop data to effectively simulate intercrop systems. The classification of the structural resource capture differences in combination with the evaluated model performance analysis allowed us to devise an evidence-based model selection criteria framework useful also for for non-specialist, while the unique detailed description provided are highly valuable for the model research community. Significance: This study establishes a conceptual framework that provides the necessary foundation for a meaningful quantitative intercomparison of intercrop models, as structural understanding enables the interpretation of numerical differences in model outputs. It also guides hypothesis testing, model choice, priorities in model development and improvements.

Accurate estimation of evapotranspiration (ET) is crucial for agricultural water management and crop yield prediction. Crop models are frequently used to simulate ET; however, model testing against detailed ET data remains scarce. The objective of this study was to evaluate nine soybean models that incorporated various approaches to estimate ET (n = 19 methods) using high resolution, multi-season eddy flux measurements from rainfed and irrigated soybean at Mead, Nebraska. Field measurements of crop growth, leaf area index (LAI), soil water content, and ET were provided to the modelers sequentially as follows: 1) phenology data for a Blind calibration; 2) irrigated crop growth; 3) irrigated daily ET and soil water; 4) rainfed ET and soil water; and 5) rainfed crop growth. Among models and ET methods, daily ET was simulated with normalized root mean square errors (nRMSE) ranging from 21.5 to 72.8 % after Full calibration, and root mean square errors (RMSE) were 0.7-2.4 mm d-1. The ensemble median across models (E-Median) reduced error in the simulation of daily ET and ranked highly across calibration steps and developmental phases. Furthermore, the E-Median showed reasonable performance under Blind calibration, with a RMSE of 0.90 mm d-1 (nRMSE= 27.7 %) for daily ET and 70.4 mm (16.7 %) for seasonal ET, indicating it can be a valuable approach for model-based ET estimation when data is scarce. This study revealed the major sources of uncertainty in simulating ET and identified opportunities for improving associated model processes, including 1) residue effects on soil evaporation during incomplete canopy cover, 2) potential ET of soybean, particularly during full canopy, and 3) leaf senescence effects on LAI during the late reproductive phase.

Background Precision agriculture (PA) is a site-specific management approach that utilises spatiotemporal information to improve productivity while also promoting sustainability. Accurate estimates of soil properties, along with the uncertainty of these estimates, are necessary for decision-making in PA. An essential soil quantity required to accurately predict crop yield is the soil organic carbon (SOC) content. To obtain the large amount of information necessary for PA implementation, the use of satellite images has become a common practice. This allows the spatial interpolation of soil properties. However, this type of indirect approach carries higher relative uncertainties than direct measurements (e.g., laboratory experiments). Although error evaluations of soil properties resulting from indirect approaches are constantly considered, the consequences of error are not.Aim This work introduces a methodology to analyse the error propagation from predictions of SOC digital maps, using the Monte Carlo (MC) method.Method We stochastically generated an error range for SOC maps, using one original map of SOC, and used these maps as inputs for a process-based model that simulated crop yields. Our approach evaluates how the error inherent in SOC observations and the subsequent spatial interpolation impacts crop yield forecasting, providing insights for decision-making and further PA implementation.Results Our results show promise in the proposed method, delivering results that are difficult to obtain. The MC method was able to handle complex, non-linear error distributions and provide a comprehensive probabilistic assessment of uncertainty, which is important for accurately predicting the impact of SOC variability on crop yield.Conclusion This method offers a degree of flexibility and robustness that is not achievable with deterministic or simpler analytical approaches, ensuring more reliable and informative insights for PA.

Escalating climate fluctuations and the increasing frequency of compound extreme weather events pose severe threats to global food security. Current operational crop yield forecasting systems, which predominantly rely on process-based models or traditional statistical approaches, often underestimate yield losses during climatic extremes due to their inability to capture complex, non-linear climate-yield dynamics. While Deep Learning (DL) offers a transformative alternative, its widespread adoption remains limited by its “black-box” nature and the difficulty of processing long agro-meteorological time series without losing critical signals from climatic anomalies. To address these gaps, we propose CropFusionNet, a novel and interpretable architecture inspired by the Temporal Fusion Transformer (TFT), designed for district-scale (NUTS-3) crop yield forecasting. CropFusionNet integrates daily time-varying climatic variables with static agro-environmental covariates and offers a more interpretable deep learning framework, enabling attribution of predictions to key environmental drivers, though not fully mechanistic. Applied to Germany’s principal crop commodities, CropFusionNet consistently outperformed established deep learning baselines and operational frameworks such as MARS and ABSOLUT. It achieved high predictive accuracy for silage maize (R2 = 0.752; MAPE = 8.66%), winter wheat (R2 = 0.597; MAPE = 8.06%), whereas, a moderate accuracy for winter barley (R2 = 0.445; MAPE = 10%), successfully capturing inter-annual variability and accurately reproducing extreme negative yield anomalies during severe drought years (2003, 2018, and 2022). Lead-time analyses further demonstrated that reliable forecasts for winter cereals (wheat and barley) can be made 40-60 days before harvest, whereas spring crops (silage maize) can be predicted up to 70 days in advance. By disentangling key environmental drivers and effectively representing non-linear system dynamics, CropFusionNet represents a fundamental transformation toward scalable, accurate, uncertainty-aware, and interpretable agricultural forecasting, providing essential support for proactive food security management. The model implementation is available at https://github.com/geonextgis/CropFusionNet.

Over the past fifty years, tomato has become one of the most extensively cultivated horticultural crops in the Mediterranean region. Climate projections for Italy indicate that temperature increases and rainfall changes will cause a 15% yield reduction in processing tomatoes, requiring an additional 85-110 mm of irrigation and 20-30 kg N ha-1 to partially offset negative impacts. Mediterranean agriculture is particularly threatened by projected climate changes in temperature and precipitation patterns. Region-specific crop models, validated against local field data, are therefore critical tools for assessing yield risks and identifying effective agronomic adaptations. Conventional process-based crop models often rely on fixed transplanting or sowing dates and harvesting dates, which fail to reflect spatiotemporal variability in management practices. Such assumptions can lead to systematic biases in regional simulations and environmental assessments. Yet phenological observations (e.g., flowering, fruit set, harvest dates) are essential for parameterizing crop models, available data typically represent point locations or experimental stations rather than the field to regional scale resolution needed for spatially explicit modelling. Sentinel-2’s high temporal frequency and spatial resolution allow tracking of within-season crop development at field scale. This study aims to: (a) compare model performance using broad agricultural land masks versus pixel-level tomato identification; and (b) evaluate whether incorporating satellite-observed canopy development dynamics (greenness trajectories, growth stage timing) reduces uncertainty in simulated crop growth, water use, and nitrogen cycling processes including nitrate leaching risk.We propose a simulation framework that combines the process-based model MONICA (Model for Nitrogen and Carbon dynamics in Agro-ecosystems) with earth observation data for processing tomatoes in the Emilia Romagna region, a major tomato production area in Italy. MONICA was calibrated and validated using four years field trials and two years on-farm data from 49 fields. We integrated two remote sensing inputs: (i) field scale processed tomato masks, and (ii) dynamic transplant and harvest dates extracted from Sentinel-2 EVI time series (validated against on-farm data, R²=0.90). We conducted regional simulations (2007-2023) comparing four model set-ups: fixed transplant and harvest dates with basic cropland mask, fixed dates with tomato masks, dynamic dates with tomato masks, and modified dynamic dates with tomato masks for sensitivity tests on transplanting date.Our research results indicate that employing specific tomato field maps combined with dynamically determined growing periods significantly improved yield simulation accuracy compared to basic cropland mask (reducing RMSE by 24%) and specific maps without consideration of remotely sensed growing season dynamics (reducing RMSE by 10%). Incorporating remote sensing data and tomato maps into the MONICA crop model also improved the model’s ability to capture yield anomalies as an indicator of its sensitivity to climatic signals, with a 24% reduction in RMSE. Integrating remote sensing-derived growing periods into crop models resulted in a wider range of simulated values, enhancing the model’s capacity to simulate nitrate leaching under real-world conditions.This study demonstrates that using remote sensing data to inform crop models significantly enhances the understanding of dynamic growth patterns, thereby supporting regional yield estimation and nitrate leaching simulations, while providing crucial insights for agricultural resource management.

The increasing number of extreme rainfall events across Europe is making waterlogging a threat to agricultural production. Prolonged soil saturation blocks the oxygen supply to roots, hindering crop growth and development. Waterlogging emerges in heterogeneous spatiotemporal patterns, which makes it difficult to quantify the resulting yield penalty. This study aims to detect waterlogging at the sub-field scale with the help of remote sensing, and to quantify associated yield losses using a process-based crop model. Waterlogging was detected using a Sentinel-1 SAR-based classification framework combining Edge–Otsu thresholding and Log-cumulant Gamma Markov Random Field (LGM) at the field scale, while Sentinel-2 derived vegetation indices were used to assess vegetation responses associated with waterlogged areas. A process-based crop model (MONICA), including a topography-based precipitation modulator, was applied to simulate waterlogging conditions leading to oxygen stress, and to quantify associated yield reductions. Analyses were conducted at both regional and field scales, with biomass reductions assessed for major winter crops and process-based yield reductions simulated for winter wheat. Regional-scale analysis revealed that crops in waterlogged areas exhibited vegetation indices 42% (triticale) to 61% (oilseed rape) lower than in non-waterlogged areas, particularly during the early growth stages. Results of the MONICA model showed a mean yield decreases of 22.6% for winter wheat in an example field under waterlogging conditions. Both remotely sensed waterlogging patterns and simulated oxygen stress consistently highlighted topographic depressions as hotspots of waterlogging impact. Incorporating a topography-based precipitation modulator into process-based MONICA simulations resulted in a strong spatial correspondence between simulated yield losses and satellite-derived biomass reductions, thereby emphasizing the importance of terrain in controlling water accumulation and waterlogging impacts.

Escalating climate fluctuations and the increasing frequency of compound extreme weather events pose severe threats to global food security. Current operational crop yield forecasting systems, which predominantly rely on process-based models or traditional statistical approaches, often underestimate yield losses during climatic extremes due to their inability to capture complex, non-linear climate-yield dynamics. While deep learning (DL) offers a transformative alternative, its widespread adoption remains limited by its “black-box” nature and the difficulty of processing long agro-meteorological time series without losing critical signals from climatic anomalies. To address these gaps, we propose CropFusionNet, a novel and interpretable architecture inspired by the Temporal Fusion Transformer (TFT), designed for district-level (NUTS-3) crop yield forecasting. CropFusionNet integrates daily time-varying climatic variables with static agro-environmental covariates and offers a more interpretable deep learning framework, enabling attribution of predictions to key environmental drivers, though not fully mechanistic. Applied to Germany's principal crop commodities, CropFusionNet consistently outperformed established deep learning baselines and operational frameworks such as MARS and ABSOLUT. It achieved high predictive accuracy for silage maize (R2 = 0.75; MAPE = 8.66%), winter wheat (R2 = 0.60; MAPE = 8.06%), and a moderate accuracy for winter barley (R2 = 0.45; MAPE = 10%), successfully capturing inter-annual variability and accurately reproducing extreme negative yield anomalies during severe drought years (2003, 2018, and 2022). Lead-time analyses further demonstrated that reliable forecasts for winter cereals (wheat and barley) can be made 40–60 days before harvest, whereas spring crops (silage maize) can be predicted up to 70 days in advance. By disentangling key environmental drivers and effectively representing non-linear system dynamics, CropFusionNet represents a fundamental transformation towards scalable, accurate, uncertainty-aware, and interpretable agricultural forecasting, providing essential support for proactive food security management. The model implementation is available at https: //github.com/geonextgis/CropFusionNet.

Crop models increasingly project that irrigation can offset agricultural losses from climate change, informing major adaptation investments worldwide. Yet these models may systematically overestimate irrigation’s protective capacity because the representation of how irrigation alters crop thermal environments remains incomplete in most large-scale assessments and assumes static efficiency under changing atmospheric conditions. More realistic assessments are urgently needed to avoid underestimating future water demands and regional adaptation failures.

Accurate crop growth monitoring is essential for effective regional agricultural management. This study investigates how the use of growing-period data and crop-specific field masks derived from remote sensing improves the accuracy of processing-tomato growth simulations. This study extracted transplanting and harvesting dates from Sentinel-2 enhanced vegetation index (EVI) time series data, demonstrating high consistency with field observations (R2 = 0.90; RMSE = 30.36 and 6.39 days, respectively). However, we observed systematic bias in transplanting dates derived from remote sensing data. For this reason, we applied a combined smoothing and interpolation approach prior to threshold detection to improve phenology retrieval; this substantially reduced transplanting date root mean square error (RMSE) from 30.36 to 27.89 days. We then calibrated and validated MONICA, a process-based crop model, using field experiments (four growing seasons) and on-farm data (49 fields - two growing seasons). Subsequently, we employed the model for eight provinces in the Emilia-Romagna region of Northern Italy to simulate crop yield under various combinations of basic cropland mask, and processingtomato mask, with and without consideration of remotely sensed growing dynamics. Results showed that employing specific tomato field maps combined with dynamic growing periods significantly improved yield simulation accuracy compared to basic cropland mask (reducing RMSE by 24%) and specific maps without consideration of remotely sensed growing season dynamics (reducing RMSE by 10%). Incorporating sensing data and tomato maps into MONICA also improved the model's ability to capture yield anomalies as an indicator of its sensitivity to climatic signals, with a 24% reduction in RMSE. Integrating remote sensing-derived growing periods into crop models resulted in a wider range of simulation values, enhancing the model's capacity to simulate nitrate leaching under real-world conditions. This study demonstrates that using remote sensing data to inform crop models significantly enhances scholarly understanding of dynamic growth patterns, supporting regional yield estimation and nitrate leaching simulations, while providing crucial insights for agricultural resource management.

ABSTRACT Nitrogen is an essential element for plant growth and, consequently, crop production. However, the cycling of nitrogen in the environment can have negative effects. Here, we review the historical development of scientific and public awareness of these effects and the influence this has had on political action to control them. Focusing on Germany as an example, we explore past nitrogen myths and how scientific progress has dispelled them, contextualizing our current position as a society seeking sufficient food, a clean environment, and an end to climate change. Given the continuous heavy burden placed on farmers to solve all these issues, we argue that from the state that we have reached today, further reducing nitrogen inputs for crop production may not necessarily lead to a further reduction in nitrogen cycling in the environment but rather to reductions in yields and product quality. Nevertheless, there is still potential to improve the efficiency of nitrogen use for stabilizing crop yields and to increase resilience against potential harm to the environment and human health. We make a couple of suggestions about what can be done.

Monitoring crop phenology is crucial for optimizing agricultural management, resource allocation, and climate adaptation. Phenological shifts, influenced by climate change, extreme weather, and management practices, affect agricultural productivity and food security. Satellite remote sensing time series capture crop biomass and chlorophyll variations to extract Land Surface Phenology (LSP) metrics, namely Start-, Peak-, and End-of-Season, linking phenological transitions to growth dynamics at field and sub-field levels. Yet, achieving both high temporal frequency and spatial detail in LSP retrieval remains a challenge, raising a key question: does integrating more data necessarily improve phenometrics retrieval accuracy? This study investigates the potential of PlanetScope (PS) and Sentinel-2 (S2) data fusion to improve LSP metrics accuracy for maize in selected test sites in Germany. Using multiple vegetation indices (Normalized Difference Vegetation Index, Normalized Difference Phenology Index, Normalized Difference Red Edge, Modified Soil-Adjusted Vegetation Index) and retrieval methods (First-of-Slope, Median, Relative-Amplitude, and Seasonal-Amplitude), we derived phenometrics from S2 and Fused datasets. A Random Forest-based model was applied to PS-S2 image pairs within a one-day interval, addressing spatial and temporal resolution trade-offs and the results were compared with several reference datasets. The results indicate significant improvements in the accuracy of emergence and harvest detection, with MAE reductions of up to 15% at early stages and similar to 8% at harvest. However, fusion outcomes for the beginning of shooting were heterogeneous, reflecting phase- and method-dependent efficacy of multi-source data. While, PS-S2 fusion demonstrates substantial potential for field-scale phenology monitoring in overall, it challenges the assumption that more data always enhances accuracy. The year-and-site-dependent variability highlights the importance of tailoring methods to phenological phase and crop type.

Climate change increasingly affects agricultural systems in Central Europe, necessitating the development of robust forecasting models for drought, heat, and fire events (DHF). These hazards pose significant threats to crop production and require proactive measures to enhance resilience and adaptation.This research project is dedicated to constructing a thorough framework for forecasting DHF events in Central Europe. It integrates an agro-ecosystem model aimed at examining how crops respond, particularly when it comes to water availability. The focus of this research extends to the region's awareness to climate-related threats and the robustness of its agricultural systems.We utilize the MONICA (Model for Nitrogen and Carbon in Agriculture) crop model to simulate crop growth and response across a spectrum of environmental conditions. The MONICA model is designed to represent the complexity of crop development, considering factors such as soil properties and weather variations. MONICA model has the capacity to explore various scenarios, including heat stress and drought sensitivity, providing a comprehensive view of how crops respond to these challenges. The used data includes high-resolution meteorological (1km resolution, daily), topographic, historical crop records and soil information for whole Germany. The dataset covers the past two decades, encompassing vital information such as crop yield records.By sensitivity analysiswe systematically identified key parameters influencing simulated crop yield and above ground biomass, particularly in the context of drought and heat stress. These insights are invaluable for advancing our understanding of how crops respond to environmental stressors.Moving forward, our focus shifts to the calibration and optimization routines to quantify specific parameter sets for individual NUTS-3 regions within Germany.In the poster presentation, we look forward to sharing the newest findings from our ongoing research on advanced calibration tools and yield simulations conducted over Germany. Simulation results are compared to observed yield data, providing valuable insights into the effectiveness and real-world applicability of the modelling approaches.

Biodiversity loss and widespread ecosystem degradation are among the most pressing challenges of our time, requiring urgent action. Yet our understanding of their causes remains limited because prevailing ecological concepts and approaches often overlook the underlying complex interactions of individuals of the same or different species, interacting with each other and with their environment. We propose a paradigm shift in ecological science, moving from simplifying frameworks that use species, population or community averages to an integrative approach that recognizes individual organisms as fundamental agents of ecological change. The urgency of the biodiversity crisis requires such a paradigm shift to advance ecology towards a predictive science by elucidating the causal mechanisms linking individual variation and adaptive behaviour to emergent properties of populations, communities, ecosystems, and ecological interactions with human interventions. Recent advances in computational technologies, sensors, and analytical tools now offer unprecedented opportunities to overcome past challenges and lay the foundation for a truly integrated Individual-Based Global Change Ecology (IBGCE). Unravelling the potential role of individual variability in global change impact analyses will require a systematic combination of empirical, experimental and modelling studies across systems, while taking into account multiple drivers of global change and their interactions. Key priorities include refining theoretical frameworks, developing benchmark models and standardized toolsets, and systematically incorporating individual variation and adaptive behaviour into empirical field work, experiments and predictive models. The emerging synergies between individual-based modelling, big data approaches, and machine learning hold great promise for addressing the inherent complexity of ecosystems. Each step in the development of IBGCE must systematically balance the complexity of the individual perspective with parsimony, computational efficiency, and experimental feasibility. IBGCE aims to unravel and predict the dynamics of biodiversity in the Anthropocene through a comprehensive study of individual organisms, their variability and their interactions. It will provide a critical foundation for considering individual variation and behaviour for future conservation and sustainability management, taking into account individual-to-ecosystem pathways and feedbacks.

Accurate simulation of evapotranspiration (ET) with crop models is essential for improving agricultural water management and yield forecasting. Few studies have evaluated multiple soybean [Glycine max (L.) Merr.] models for simulating ET under conditions of low evaporative demand that is characteristic for a warm-summer humid continental climate. Six soybean crop models, encompassing 15 different modeling approaches, were evaluated for ET simulation and compared against eddy covariance data collected over five growing seasons in Ottawa, Canada. Models were first calibrated with phenology, in-season growth, and yield data, followed by calibration with measured ET and soil water content (SWC) data during the second step. After initial calibration, simulated daily ET was higher on average than measured ET, particularly during full canopy cover (normalized bias, nBias = 17.1 to 49.2% depending on the model). Following the second calibration, simulated daily ET was closer to measured values, but bias remained (nBias = 5.9 to 52.1% during full canopy). The ensemble median reduced uncertainty in the simulation of daily ET compared to most models, but DNDC remained the top-ranking model (nRMSE = 0.7 mm d- 1, nBias = 11.2%). The MONICA model was most accurate simulating cumulative ET (RMSE = 39.9 mm, nBias = 11.3%), whereas the CROPGRO models excelled simulating SWC (RMSE= 0.04 to 0.05 m3 m- 3, nBias = 0.10 to 0.9% depending on soil depth). This study was instrumental in evaluating the best ET methodologies and parameters in soybean models. However, there was bias across the models compared to measured eddy covariance ET in a humid environment. The results reveal the need to further investigate possible biases in ET estimates by eddy covariance over soybean canopies, and to review the role of night-time dew contributions to ET in process-based models.