FOSS4G 2025 | GeoAI Transformer–LSTM Boosts Maize-Yield Accuracy in Malawi’s Smallholder Fields скачать в хорошем качестве

FOSS4G 2025 | GeoAI Transformer–LSTM Boosts Maize-Yield Accuracy in Malawi’s Smallholder Fields

Presented by Kondwani Munthali, Mathews Jere on 19 November 2025 16:30, at FOSS4G 2025 Auckland. Track: Academic Full presentation details - https://talks.osgeo.org/foss4g-2025/t... WPLVJQ Leave-one-field-out tests on Malawian smallholder plots compare multiband/index linear regression, XGBoost, CNN-LSTM, a frozen ViT and a ViT-LSTM on Sentinel-2 VT–R1 stacks. ViT-LSTM delivers the best accuracy (RMSE 0.022 t ha⁻¹) but runs 2.5 × slower than CNN-LSTM. 1. Introduction Maize supplies almost 60 % of Malawi’s caloric intake, so mid-season yield forecasts are pivotal for food-security planning (FAO, 2015). Conventional ground surveys reach farmers only after harvest and sample less than 1 % of the 1.8 million smallholdings. Optical earth-observation offers plot-scale coverage, and deep learning is now outperforming index-based regressions (Muruganantham et al., 2022). Transformers have recently eclipsed CNNs in US Corn-Belt studies (Lin et al., 2023), yet their benefit for densely inter-cropped African fields is unknown. We therefore benchmark five modelling paradigms, ranging from linear regression to a novel Vision-Transformer–LSTM (ViT-LSTM) hybrid, on a hand-harvested dataset from Zomba District. [...] All models were implemented in PyTorch 2.3 and trained on an NVIDIA Quadro P1000 GPU. Hyper-parameters were optimised with Optuna. Deep networks trained for 50 epochs using AdamW, cosine-annealed learning rates, batch = 1, FP16 mixed precision, and early-stopping (patience = 10). A leave-one-field-out (LOFO) scheme ensured each field served once as the unseen test set. Performance was assessed with RMSE and MAE. Exact paired-permutation tests compared fold-wise RMSEs, and average inference time per tile was computed for every fold. All code, configuration files, and anonymised data are released under GPL-3.0 at https://github.com/jahnical/yield-pre..., enabling full replication of the workflow. 3. Results Accuracy: ViT-LSTM achieved the lowest cross-validated RMSE 0.022 t ha⁻¹ and MAE 0.019 t ha⁻¹. CNN-LSTM followed at RMSE 0.088 t ha⁻¹; frozen ViT, 0.219 t ha⁻¹. XGBoost and LR-Indices exceeded 0.22 t ha⁻¹. Significance: Both recurrent models (CNN-LSTM and ViT-LSTM) significantly out-performed non-recurrent baselines (p ≤ 0.02). The gap between ViT-LSTM and CNN-LSTM was also significant (p = 0.046). Speed: LR-Indices and XGBoost predicted in less than 0.02 ms per tile. CNN-LSTM needed 14 ms, whereas ViT-LSTM required 36 ms, 2.5 times slower. 4. Discussion Explicit spatio-temporal learning is critical because Malawi’s smallholder plots are tiny, irregular and often inter-cropped; spectral signatures therefore vary sharply over just a few metres and change quickly as plants develop. Recurrent layers already capture the crop’s phenological curve, but the self-attention blocks in the transformer let the model weigh non-contiguous pixels and dates, teasing out subtle edge effects and mixed-crop patterns that a CNN-LSTM misses (Liu et. el, 2023). That extra context cuts RMSE by ≈ 0.07 t ha⁻¹ (about 60 %), yet self-attention is quadratic in sequence length, so inference jumps from 14 ms to 36 ms per 32 by 32 px 1 m-tile, a 2.5× latency cost. Data is streamed through Google Earth Engine, a free (though not open-source) cloud platform, while QGIS for vector editing, Rasterio/xarray for raster I/O, and PyTorch/XGBoost for modelling are fully open-source. This workflow demonstrates how combining free cloud access with FOSS4G tools can deliver high-resolution, scalable yield mapping in resource-constrained settings. 5. Conclusion We present the first open-source, plot-scale benchmark that pits classical machine-learning models, CNN-LSTM, and a transformer–recurrent hybrid on Malawian maize yields. ViT-LSTM attains state-of-the-art accuracy (RMSE 0.022 t ha⁻¹), an 60 % improvement over CNN-LSTM, at a four-fold latency cost. All code and data are freely released, inviting the FOSS4G community to replicate, critique, and extend the workflow to other crops, sensors, and regions. === https://2025.foss4g.org/ ‪@FOSS4G‬