Ioannis N. Athanasiadis

Ilias Tsoumas, Georgios Giannarakis, Vasileios Sitokonstantinou et al.

In contrast to the rapid digitalization of several industries, agriculture suffers from low adoption of smart farming tools. While AI-driven digital agriculture tools can offer high-performing predictive functionalities, they lack tangible quantitative evidence on their benefits to the farmers. Field experiments can derive such evidence, but are often costly, time consuming and hence limited in scope and scale of application. To this end, we propose an observational causal inference framework for the empirical evaluation of the impact of digital tools on target farm performance indicators (e.g., yield in this case). This way, we can increase farmers' trust via enhancing the transparency of the digital agriculture market and accelerate the adoption of technologies that aim to secure farmer income resilience and global agricultural sustainability. As a case study, we designed and implemented a recommendation system for the optimal sowing time of cotton based on numerical weather predictions, which was used by a farmers' cooperative during the growing season of 2021. We then leverage agricultural knowledge, collected yield data, and environmental information to develop a causal graph of the farm system. Using the back-door criterion, we identify the impact of sowing recommendations on the yield and subsequently estimate it using linear regression, matching, inverse propensity score weighting and meta-learners. The results reveal that a field sown according to our recommendations exhibited a statistically significant yield increase that ranged from 12% to 17%, depending on the method. The effect estimates were robust, as indicated by the agreement among the estimation methods and four successful refutation tests. We argue that this approach can be implemented for decision support systems of other fields, extending their evaluation beyond a performance assessment of internal functionalities.

Diego Marcos, Robert van de Vlasakker, Ioannis N. Athanasiadis et al.

Plant morphological traits, their observable characteristics, are fundamental to understand the role played by each species within their ecosystem. However, compiling trait information for even a moderate number of species is a demanding task that may take experts years to accomplish. At the same time, massive amounts of information about species descriptions is available online in the form of text, although the lack of structure makes this source of data impossible to use at scale. To overcome this, we propose to leverage recent advances in large language models (LLMs) and devise a mechanism for gathering and processing information on plant traits in the form of unstructured textual descriptions, without manual curation. We evaluate our approach by automatically replicating three manually created species-trait matrices. Our method managed to find values for over half of all species-trait pairs, with an F1-score of over 75%. Our results suggest that large-scale creation of structured trait databases from unstructured online text is currently feasible thanks to the information extraction capabilities of LLMs, being limited by the availability of textual descriptions covering all the traits of interest.

Dilli R. Paudel, Diego Marcos, Allard de Wit et al.

Predictor inputs and label data for crop yield forecasting are not always available at the same spatial resolution. We propose a deep learning framework that uses high resolution inputs and low resolution labels to produce crop yield forecasts for both spatial levels. The forecasting model is calibrated by weak supervision from low resolution crop area and yield statistics. We evaluated the framework by disaggregating regional yields in Europe from parent statistical regions to sub-regions for five countries (Germany, Spain, France, Hungary, Italy) and two crops (soft wheat and potatoes). Performance of weakly supervised models was compared with linear trend models and Gradient-Boosted Decision Trees (GBDT). Higher resolution crop yield forecasts are useful to policymakers and other stakeholders. Weakly supervised deep learning methods provide a way to produce such forecasts even in the absence of high resolution yield data.

Vasileios Sitokonstantinou, Emiliano Díaz Salas Porras, Jordi Cerdà Bautista et al.

In a changing climate, sustainable agriculture is essential for food security and environmental health. However, it is challenging to understand the complex interactions among its biophysical, social, and economic components. Predictive machine learning (ML), with its capacity to learn from data, is leveraged in sustainable agriculture for applications like yield prediction and weather forecasting. Nevertheless, it cannot explain causal mechanisms and remains descriptive rather than prescriptive. To address this gap, we propose causal ML, which merges ML's data processing with causality's ability to reason about change. This facilitates quantifying intervention impacts for evidence-based decision-making and enhances predictive model robustness. We showcase causal ML through eight diverse applications that benefit stakeholders across the agri-food chain, including farmers, policymakers, and researchers.

Ioannis Athanasiadis, Anmar Karmush, Michael Felsberg

In deep learning, functional similarity evaluation quantifies the extent to which independently trained models learn similar input--output relationships. In model stitching, functional similarity is framed as representation forward compatibility, i.e., whether the representations of two models can be aligned to solve a given task. Recent studies, however, highlight a critical limitation: models relying on different information cues can still produce compatible representations, making them appear misleadingly similar (Smith et al., 2025). We attribute this failure to standard model stitching being inherently blind to the invariance properties of the stitched models. To address this limitation, we introduce the forward--backward compatibility requirement under which we formulate the invariance-aware model stitching. Through analyzing key stitching configurations, we study the interplay between forward and backward compatibility, showing that invariance-aware model stitching provides a more principled approach to functional similarity evaluation while revealing functional discrepancies previously obscured.

Michiel G. J. Kallenberg, Bernardo Maestrini, Ron van Bree et al.

Crop yield prediction typically involves the utilization of either theory-driven process-based crop growth models, which have proven to be difficult to calibrate for local conditions, or data-driven machine learning methods, which are known to require large datasets. In this work we investigate potato yield prediction using a hybrid meta-modeling approach. A crop growth model is employed to generate synthetic data for (pre)training a convolutional neural net, which is then fine-tuned with observational data. When applied in silico, our meta-modeling approach yields better predictions than a baseline comprising a purely data-driven approach. When tested on real-world data from field trials (n=303) and commercial fields (n=77), the meta-modeling approach yields competitive results with respect to the crop growth model. In the latter set, however, both models perform worse than a simple linear regression with a hand-picked feature set and dedicated preprocessing designed by domain experts. Our findings indicate the potential of meta-modeling for accurate crop yield prediction; however, further advancements and validation using extensive real-world datasets is recommended to solidify its practical effectiveness.

Ilias Tsoumas, Georgios Giannarakis, Vasileios Sitokonstantinou et al.

In contrast to the rapid digitalization of several industries, agriculture suffers from low adoption of climate-smart farming tools. Even though AI-driven digital agriculture can offer high-performing predictive functionalities, it lacks tangible quantitative evidence on its benefits to the farmers. Field experiments can derive such evidence, but are often costly and time consuming. To this end, we propose an observational causal inference framework for the empirical evaluation of the impact of digital tools on target farm performance indicators. This way, we can increase farmers' trust by enhancing the transparency of the digital agriculture market, and in turn accelerate the adoption of technologies that aim to increase productivity and secure a sustainable and resilient agriculture against a changing climate. As a case study, we perform an empirical evaluation of a recommendation system for optimal cotton sowing, which was used by a farmers' cooperative during the growing season of 2021. We leverage agricultural knowledge to develop a causal graph of the farm system, we use the back-door criterion to identify the impact of recommendations on the yield and subsequently estimate it using several methods on observational data. The results show that a field sown according to our recommendations enjoyed a significant increase in yield (12% to 17%).

Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn et al.

Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, recent studies show that PINN optimisation is sensitive to numerical precision. Existing implementations commonly use either single precision (FP32), which is computationally efficient but prone to failure modes, or double precision (FP64), which is robust but substantially expensive. This creates a trade-off between computational efficiency and numerical accuracy. To reduce the computational cost of double-precision training while retaining prediction accuracy, we propose a curvature-aware precision controller that adapts numerical precision during training rather than treating it as a fixed implementation choice. The proposed method reuses curvature information derived from the limited-memory BFGS (L-BFGS) optimiser to construct a precision controller, retaining FP32 when lower precision is sufficient and promoting computation to FP64 when the training dynamics indicate numerical sensitivity or precision-limited stagnation. We evaluate the proposed approach on four canonical PINN failure-mode benchmarks and an irradiance-driven ordinary differential equation example. We further test the proposed approach across different neural network architectures. The method consistently matches or even slightly exceeds full FP64 solution accuracy while reducing training time relative to full double-precision training on all benchmark equations. The obtained results indicate that precision sensitivity in PINN optimisation is phase-dependent, and that selectively applying higher precision only during numerically critical stages can lower computational cost without sacrificing predictive accuracy.

Christos Pylianidis, Ioannis N. Athanasiadis

Learning latent representations has aided operational decision-making in several disciplines. Its advantages include uncovering hidden interactions in data and automating procedures which were performed manually in the past. Representation learning is also being adopted by earth and environmental sciences. However, there are still subfields that depend on manual feature engineering based on expert knowledge and the use of algorithms which do not utilize the latent space. Relying on those techniques can inhibit operational decision-making since they impose data constraints and inhibit automation. In this work, we adopt a case study for nitrogen response rate prediction and examine if representation learning can be used for operational use. We compare a Multilayer Perceptron, an Autoencoder, and a dual-head Autoencoder with a reference Random Forest model for nitrogen response rate prediction. To bring the predictions closer to an operational setting we assume absence of future weather data, and we are evaluating the models using error metrics and a domain-derived error threshold. The results show that learning latent representations can provide operational nitrogen response rate predictions by offering performance equal and sometimes better than the reference model.

Thijs L van der Plas, Jacob JW Bakermans, Vishal Nedungadi et al.

Earth embedding models transform Earth observation data into embeddings uniquely tied to locations on the Earth's surface. These models are typically evaluated in isolation, comparing the downstream task performance across different Earth embeddings. However, spatially aligned embeddings can naturally be fused, providing richer information per location, a capability that isolated evaluations fail to capture. We therefore propose assessing Earth embeddings by their complementarity: the performance gain of fused embeddings over the best single-model baseline. To operationalise this, we introduce an embedding complementarity index applicable to any embedding and task, and evaluate four Earth embedding models (AlphaEarth, Tessera, GeoCLIP, SatCLIP) in isolation, in all pairs, and jointly across six downstream tasks. Fused embeddings outperform the best single model in four out of six tasks, confirming that single-embedding evaluations often underestimate Earth embedding capabilities. Complementarity proves both task- and location-dependent. Further, for a land cover regression task, we find that complementarity is partially determined by the spatial scale of land cover classes. Complementarity reframes Earth embeddings: the greatest future gains may come not from any single Earth embedding model, but from combinations that are better together.

Aike Potze, Fred van Eeuwijk, Ioannis N. Athanasiadis

Plant breeding underpins global food security through incremental, accumulating improvements in crop yield, quality and sustainability, achieved via repeated cycles of crop ranking, selection and crossing. Climate change disrupts this process by altering local growing conditions, thereby shifting the relative performance of crop genotypes. Predicting these relative changes in yield is critical for food security. Yet, this problem remains an open challenge in plant breeding, and relatively unexplored within the AI community. We propose MixINN, an approach that first isolates high-quality genotype-environment interaction labels using mixed models, and then predicts these interactions for new crop varieties in future environmental conditions with a deep neural network. We evaluate our method on a corn multi-environment trial across the continental United States and show improved prediction of genotype ranking over current plant breeding methods. MixINN demonstrated superior performance in identifying the 20% most productive corn genotypes, leading to a 5.8% higher average yield, which further improved to 7.2% when targeting specific growing environments. These are competitive results for real-world breeding programs, demonstrating the potential of AI research in accelerating the development of climate-adapted crops, and improving future food security under climate change.

Eva van Tegelen, Taniya Kapoor, George A. K. van Voorn et al.

Developing neural operators that accurately predict the behavior of systems governed by partial differential equations (PDEs) across unseen parameter regimes is crucial for robust generalization in scientific and engineering applications. In practical applications, variations in physical parameters induce distribution shifts between training and prediction regimes, making extrapolation a central challenge. As a result, the way parameters are incorporated into neural operator models plays a key role in their ability to generalize, particularly when state and parameter representations are entangled. In this work, we introduce the Late Fusion Neural Operator, an architecture that disentangles learning state dynamics from parameter effects, improving predictive performance both within and beyond the training distribution. Our approach combines neural operators for learning latent state representations with sparse regression to incorporate parameter information in a structured manner. Across four benchmark PDEs including advection, Burgers, and both 1D and 2D reaction-diffusion equations, the proposed method consistently outperforms Fourier Neural Operator and CAPE-FNO. Late Fusion Neural Operators achieve consistently the best performance in all experiments, with an average RMSE reduction of 72.9% in-domain and 71.8% out-domain compared to the second-best method. These results demonstrate strong generalization across both in-domain and out-domain parameter regimes.

Vishal Nedungadi, Muhammad Akhtar Munir, Marc Rußwurm et al.

Air pollution remains a leading global health risk, exacerbated by rapid industrialization and urbanization, contributing significantly to morbidity and mortality rates. In this paper, we introduce AirCast, a novel multi-variable air pollution forecasting model, by combining weather and air quality variables. AirCast employs a multi-task head architecture that simultaneously forecasts atmospheric conditions and pollutant concentrations, improving its understanding of how weather patterns affect air quality. Predicting extreme pollution events is challenging due to their rare occurrence in historic data, resulting in a heavy-tailed distribution of pollution levels. To address this, we propose a novel Frequency-weighted Mean Absolute Error (fMAE) loss, adapted from the class-balanced loss for regression tasks. Informed from domain knowledge, we investigate the selection of key variables known to influence pollution levels. Additionally, we align existing weather and chemical datasets across spatial and temporal dimensions. AirCast's integrated approach, combining multi-task learning, frequency weighted loss and domain informed variable selection, enables more accurate pollution forecasts. Our source code and models are made public here (https://github.com/vishalned/AirCast.git)

Ioannis Athanasiadis, Fredrik Lindsten, Michael Felsberg

Variational Autoencoders (VAEs) are a popular framework for unsupervised learning and data generation. A plethora of methods have been proposed focusing on improving VAEs, with the incorporation of adversarial objectives and the integration of prior learning mechanisms being prominent directions. When it comes to the former, an indicative instance is the recently introduced family of Introspective VAEs aiming at ensuring that a low likelihood is assigned to unrealistic samples. In this study, we focus on the Soft-IntroVAE (S-IntroVAE), one of only two members of the Introspective VAE family, the other being the original IntroVAE. We select S-IntroVAE for its state-of-the-art status and its training stability. In particular, we investigate the implication of incorporating a multimodal and trainable prior into this S-IntroVAE. Namely, we formulate the prior as a third player and show that when trained in cooperation with the decoder constitutes an effective way for prior learning, which shares the Nash Equilibrium with the vanilla S-IntroVAE. Furthermore, based on a modified formulation of the optimal ELBO in S-IntroVAE, we develop theoretically motivated regularizations, namely (i) adaptive variance clipping to stabilize training when learning the prior and (ii) responsibility regularization to discourage the formation of inactive prior modes. Finally, we perform a series of targeted experiments on a 2D density estimation benchmark and in an image generation setting comprised of the (F)-MNIST and CIFAR-10 datasets demonstrating the effect of prior learning in S-IntroVAE in generation and representation learning.

Ron van Bree, Diego Marcos, Ioannis Athanasiadis

Biophysical models offer valuable insights into climate-phenology relationships in both natural and agricultural settings. However, there are substantial structural discrepancies across models which require site-specific recalibration, often yielding inconsistent predictions under similar climate scenarios. Machine learning methods offer data-driven solutions, but often lack interpretability and alignment with existing knowledge. We present a phenology model describing dormancy in fruit trees, integrating conventional biophysical models with a neural network to address their structural disparities. We evaluate our hybrid model in an extensive case study predicting cherry tree phenology in Japan, South Korea and Switzerland. Our approach consistently outperforms both traditional biophysical and machine learning models in predicting blooming dates across years. Additionally, the neural network's adaptability facilitates parameter learning for specific tree varieties, enabling robust generalization to new sites without site-specific recalibration. This hybrid model leverages both biophysical constraints and data-driven flexibility, offering a promising avenue for accurate and interpretable phenology modeling.

Hilmy Baja, Michiel Kallenberg, Ioannis N. Athanasiadis

Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive, time-consuming and expensive. In most cases, it is not feasible to gather crop state measurements before every decision moment. Moreover, in previous research pertaining to farm management optimization, these observations are often assumed to be readily available without any cost, which is unrealistic. Hence, enabling optimization without the need to have temporally complete crop state observations is important. An approach to that problem is to include measuring as part of decision making. As a solution, we apply reinforcement learning (RL) to recommend opportune moments to simultaneously measure crop features and apply nitrogen fertilizer. With realistic considerations, we design an RL environment with explicit crop feature measuring costs. While balancing costs, we find that an RL agent, trained with recurrent PPO, discovers adaptive measuring policies that follow critical crop development stages, with results aligned by what domain experts would consider a sensible approach. Our results highlight the importance of measuring when crop feature measurements are not readily available.

Ilias Tsoumas, Vasileios Sitokonstantinou, Georgios Giannarakis et al.

Pesticides serve as a common tool in agricultural pest control but significantly contribute to the climate crisis. To combat this, Integrated Pest Management (IPM) stands as a climate-smart alternative. Despite its potential, IPM faces low adoption rates due to farmers' skepticism about its effectiveness. To address this challenge, we introduce an advanced data analysis framework tailored to enhance IPM adoption. Our framework provides i) robust pest population predictions across diverse environments with invariant and causal learning, ii) interpretable pest presence predictions using transparent models, iii) actionable advice through counterfactual explanations for in-season IPM interventions, iv) field-specific treatment effect estimations, and v) assessments of the effectiveness of our advice using causal inference. By incorporating these features, our framework aims to alleviate skepticism and encourage wider adoption of IPM practices among farmers.

Zehao Lu, Thijs L van der Plas, Parinaz Rashidi et al.

Large, open datasets can accelerate ecological research, particularly by enabling researchers to develop new insights by reusing datasets from multiple sources. However, to find the most suitable datasets to combine and integrate, researchers must navigate diverse ecological and environmental data provider platforms with varying metadata availability and standards. To overcome this obstacle, we have developed a large language model (LLM)-based metadata harvester that flexibly extracts metadata from any dataset's landing page, and converts these to a user-defined, unified format using existing metadata standards. We validate that our tool is able to extract both structured and unstructured metadata with equal accuracy, aided by our LLM post-processing protocol. Furthermore, we utilise LLMs to identify links between datasets, both by calculating embedding similarity and by unifying the formats of extracted metadata to enable rule-based processing. Our tool, which flexibly links the metadata of different datasets, can therefore be used for ontology creation or graph-based queries, for example, to find relevant ecological and environmental datasets in a virtual research environment.

Eva van Tegelen, George van Voorn, Ioannis Athanasiadis et al.

Forecasting system behaviour near and across bifurcations is crucial for identifying potential shifts in dynamical systems. While machine learning has recently been used to learn critical transitions and bifurcation structures from data, most studies remain limited as they exclusively focus on discrete-time methods and local bifurcations. To address these limitations, we use Neural Ordinary Differential Equations which provide a data-driven framework for learning system dynamics. Our results show that Neural Ordinary Differential Equations can recover underlying bifurcation structures directly from time-series data by learning parameter-dependent vector fields. Notably, we demonstrate that Neural Ordinary Differential Equations can forecast bifurcations even beyond the parameter regions represented in the training data. We demonstrate our approach on three test cases: the Lorenz system transitioning from non-chaotic to chaotic behaviour, the Rössler system moving from chaos to period doubling, and a predator-prey model exhibiting collapse via a global bifurcation.

Ilias Tsoumas, Dimitrios Bormpoudakis, Vasileios Sitokonstantinou et al.

In causal inference, whether through randomized controlled trials or observational studies, access to both treated and control units is essential for estimating the effect of a treatment on an outcome of interest. When treatment assignment is random, the average treatment effect (ATE) can be estimated directly by comparing outcomes between groups. In non-randomized settings, various techniques are employed to adjust for confounding and approximate the counterfactual scenario to recover an unbiased ATE. A common challenge, especially in observational studies, is the absence of units clearly labeled as controls-that is, units known not to have received the treatment. To address this, we propose positive-unlabeled (PU) learning as a framework for identifying, with high confidence, control units from a pool of unlabeled ones, using only the available treated (positive) units. We evaluate this approach using both simulated and real-world data. We construct a causal graph with diverse relationships and use it to generate synthetic data under various scenarios, assessing how reliably the method recovers control groups that allow estimates of true ATE. We also apply our approach to real-world data on optimal sowing and fertilizer treatments in sustainable agriculture. Our findings show that PU learning can successfully identify control (negative) units from unlabeled data based only on treated units and, through the resulting control group, estimate an ATE that closely approximates the true value. This work has important implications for observational causal inference, especially in fields where randomized experiments are difficult or costly. In domains such as earth, environmental, and agricultural sciences, it enables a plethora of quasi-experiments by leveraging available earth observation and climate data, particularly when treated units are available but control units are lacking.

Alkis Sygkounas, Ioannis Athanasiadis, Andreas Persson et al.

Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL) approach that enhances Reinforcement Learning (RL) by merging human insights directly into the RL training process, improving model performance. Our proposed iDDQN method modifies the Q-value update equation to integrate human and agent actions, establishing a collaborative approach for policy development. Additionally, we present an offline evaluative framework that simulates the agent's trajectory as if no human intervention had occurred, to assess the effectiveness of human interventions. Empirical results in simulated autonomous driving scenarios demonstrate that iDDQN outperforms established approaches, including Behavioral Cloning (BC), HG-DAgger, Deep Q-Learning from Demonstrations (DQfD), and vanilla DRL in leveraging human expertise for improving performance and adaptability.

Omar G. Younis, Luca Corinzia, Ioannis N. Athanasiadis et al.

Crop breeding is crucial in improving agricultural productivity while potentially decreasing land usage, greenhouse gas emissions, and water consumption. However, breeding programs are challenging due to long turnover times, high-dimensional decision spaces, long-term objectives, and the need to adapt to rapid climate change. This paper introduces the use of Reinforcement Learning (RL) to optimize simulated crop breeding programs. RL agents are trained to make optimal crop selection and cross-breeding decisions based on genetic information. To benchmark RL-based breeding algorithms, we introduce a suite of Gym environments. The study demonstrates the superiority of RL techniques over standard practices in terms of genetic gain when simulated in silico using real-world genomic maize data.

Hiske Overweg, Herman N. C. Berghuijs, Ioannis N. Athanasiadis

Nitrogen fertilizers have a detrimental effect on the environment, which can be reduced by optimizing fertilizer management strategies. We implement an OpenAI Gym environment where a reinforcement learning agent can learn fertilization management policies using process-based crop growth models and identify policies with reduced environmental impact. In our environment, an agent trained with the Proximal Policy Optimization algorithm is more successful at reducing environmental impacts than the other baseline agents we present.

Ioannis Athanasiadis, Panagiotis Mousouliotis, Loukas Petrou

Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks which are suitable for object detection in real time embedded applications, such as the SqueezeDet neural network. We use transfer learning to accelerate the training of SqueezeDet to a new group of classes. Also, experiments are conducted to study the transferability and co-adaptation phenomena introduced by the transfer learning process. To accelerate training, we propose a new implementation of the SqueezeDet training which provides a faster pipeline for data processing and achieves 1.8 times speedup compared to the initial implementation. Finally, we created a mechanism for automatic hyperparameter optimization using an empirical method.