Tabular models predict irrigation water height well within same sector
Scenario Generalization and Sector Transfer in Real Surface Irrigation Surrogate Modelling with Tabular Models
Machine Learning
Summary
Planning surface irrigation requires testing many scenarios, but detailed simulations are expensive. The authors study simpler tabular models that predict the highest water level using drone data and field details. They find these models work well when predicting new scenarios in the same field area but struggle when applied to different field shapes or areas. Adjusting data coordinates helps somewhat but does not fully solve the problem.
What this means in practice
- •For irrigation system planners: Use tabular surrogate models to quickly screen water height outcomes under many planning scenarios in a single field sector without running expensive simulations.
- •For geospatial data engineers: Incorporate sector-frame normalization techniques when transferring irrigation prediction models between similarly shaped fields to improve accuracy.
Authors
Alessandro Cagiano, M. Aybars Seyhan, Fabiola Gangi, Matteo Zignani, Daniele Masseroni
Abstract
Surface irrigation planning requires screening many operating conditions and spatial configurations, while high-fidelity shallow-water-equation (SWE) simulations are expensive. We study tabular surrogate models for predicting maximum water height from drone-derived field morphology, terrain, hydrological, spatial, and scenario descriptors, where each row represents a spatial cell under one irrigation scenario. To assess deployment feasibility, we evaluate gradient-boosted trees, neural tabular models, AutoML, and tabular foundation models (TFMs) under two regimes: same-sector generalization, where a model predicts unseen scenarios after observing a limited set of configurations in the same sector, and sector-out transfer, where knowledge learned from source sectors is transferred to an unseen sector. The main findings are twofold: a) under the evaluated fixed 8/32 same-sector split, surrogates achieve strong performance, especially with raw spatial coordinates; b) sector-out transfer is substantially harder because the target sector has different coordinates and geometry. Sector-frame normalization of spatial coordinates improves transfer across similarly structured sectors, but does not solve cross-shape generalization. Overall, tabular surrogates appear useful for same-sector scenario screening under this fixed split, while robust transfer to unseen sectors remains open.