Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data

• URL: http://arxiv.org/abs/2510.07350v1
• Date: Wed, 08 Oct 2025 03:27:12 GMT
• Title: Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
• Authors: Aditya Chakravarty,
• Abstract summary: We benchmark two state-of-the-art deep learning models, GNN-RNN and MMST-ViT, under realistic out-of-distribution conditions.<n>GNN-RNN demonstrates superior generalization with positive correlations under geographic shifts, while MMST-ViT performs well in-domain but degrades sharply under OOD conditions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Climate change is increasingly disrupting agricultural systems, making accurate crop yield forecasting essential for food security. While deep learning models have shown promise in yield prediction using satellite and weather data, their ability to generalize across geographic regions and years - critical for real-world deployment - remains largely untested. We benchmark two state-of-the-art models, GNN-RNN and MMST-ViT, under realistic out-of-distribution (OOD) conditions using the large-scale CropNet dataset spanning 1,200+ U.S. counties from 2017-2022. Through leave-one-cluster-out cross-validation across seven USDA Farm Resource Regions and year-ahead prediction scenarios, we identify substantial variability in cross-region transferability. GNN-RNN demonstrates superior generalization with positive correlations under geographic shifts, while MMST-ViT performs well in-domain but degrades sharply under OOD conditions. Regions like Heartland and Northern Great Plains show stable transfer dynamics (RMSE less than 10 bu/acre for soybean), whereas Prairie Gateway exhibits persistent underperformance (RMSE greater than 20 bu/acre) across both models and crops, revealing structural dissimilarities likely driven by semi-arid climate, irrigation patterns, and incomplete spectral coverage. Beyond accuracy differences, GNN-RNN achieves 135x faster training than MMST-ViT (14 minutes vs. 31.5 hours), making it more viable for sustainable deployment. Our findings underscore that spatial-temporal alignment - not merely model complexity or data scale - is key to robust generalization, and highlight the need for transparent OOD evaluation protocols to ensure equitable and reliable climate-aware agricultural forecasting.

Related papers

• Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting [99.4484686548807]
  We propose OmniAir, a semantic topology learning framework tailored for global station-level prediction.<n>Our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks.<n>Experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models.
  arXiv  Detail & Related papers  (2026-01-29T15:58:07Z)
• Long-Term Probabilistic Forecast of Vegetation Conditions Using Climate Attributes in the Four Corners Region [0.40022988333495174]
  We develop a two-phase machine learning model to forecast the one-year-ahead peak NDVI over high-resolution grids.<n>We develop open-source tools that outperform alternative methods for both gross NDVI and grid-based NDVI one-year forecasts.
  arXiv  Detail & Related papers  (2026-01-22T22:10:29Z)
• Synergistic Neural Forecasting of Air Pollution with Stochastic Sampling [50.3911487821783]
  Air pollution remains a leading global health and environmental risk, particularly in regions vulnerable to episodic air pollution spikes due to wildfires, urban haze and dust storms.<n>Here, we present SynCast, a high-resolution neural forecasting model that integrates meteorological and air composition data to improve predictions of both average and extreme pollution levels.
  arXiv  Detail & Related papers  (2025-10-28T01:18:00Z)
• Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift [2.5551933647600693]
  Causal modeling offers a principled foundation for uncovering stable, invariant relationships in time-series data.<n>We propose RIC-TSC, a regionally-informed causal time-series classification framework that embeds lag-aware causal discovery directly into sequence modeling.
  arXiv  Detail & Related papers  (2025-10-17T03:06:08Z)
• VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting [1.1470070927586018]
  Current AI models systematically underperform when yields deviate from historical trends.<n>We introduce VITA, a variational pretraining framework that learns representations from large satellite-based weather datasets.<n>VITA is applied to 763 counties in the U.S. Corn Belt and achieves state-of-the-art performance in predicting corn and soybean yields.
  arXiv  Detail & Related papers  (2025-08-05T15:56:36Z)
• OneForecast: A Universal Framework for Global and Regional Weather Forecasting [67.61381313555091]
  We propose a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks.<n>By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region.<n>We introduce an adaptive messaging mechanism, using dynamic gating units, to deeply integrate node and edge features for more accurate extreme event forecasting.
  arXiv  Detail & Related papers  (2025-02-01T06:49:16Z)
• FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting [56.73502043159699]
  This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution. It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model. The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
  arXiv  Detail & Related papers  (2024-01-28T13:23:25Z)
• A Hybrid Deep Learning-based Approach for Optimal Genotype by Environment Selection [8.084449311613517]
  We used a dataset comprising 93,028 training records to forecast yields for 10,337 test records, covering 159 locations over 13 years (2003-2015) This dataset included details on 5,838 distinct genotypes and daily weather data for a 214-day growing season, enabling comprehensive analysis. We developed two novel convolutional neural network (CNN) architectures: the CNN-DNN model, combining CNN and fully-connected networks, and the CNN-LSTM-DNN model, with an added LSTM layer for weather variables.
  arXiv  Detail & Related papers  (2023-09-22T17:31:47Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Increasing the accuracy and resolution of precipitation forecasts using deep generative models [3.8073142980733]
  We train a conditional Generative Adversarial Network -- coined CorrectorGAN -- to produce ensembles of high-resolution, bias-corrected forecasts. CorrectorGAN, once trained, produces predictions in seconds on a single machine. Results raise exciting questions about the necessity of regional models, and whether data-driven downscaling and correction methods can be transferred to data-poor regions.
  arXiv  Detail & Related papers  (2022-03-23T09:45:12Z)
• Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
  We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
  arXiv  Detail & Related papers  (2022-02-10T11:37:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.