Modular, On-Site Solutions with Lightweight Anomaly Detection for Sustainable Nutrient Management in Agriculture.

Abstract

Efficient nutrient management is critical for crop growth and sustainable resource consumption (e.g., nitrogen and energy). Current approaches require lengthy analyses, preventing real-time optimization; similarly, imaging facilitates rapid phenotyping but can be computationally intensive, preventing deployment under resource constraints. This study proposes a flexible, tiered pipeline for anomaly detection and status estimation (fresh weight, dry mass, and tissue nutrients), including a comprehensive energy analysis of approaches that span the efficiency-accuracy spectrum. Using a nutrient depletion experiment with three treatments (T1-100%, T2-50%, and T3-25% fertilizer strength) and multispectral imaging, we developed a hierarchical pipeline using an autoencoder for early warning. Further, we compared two status estimation modules of different complexity for more detailed analysis: vegetation index features with machine learning (random forest, RF) and raw whole-image deep learning (vision transformer, ViT). Results demonstrated high-efficiency anomaly detection (73% net detection of T3 samples 9 days after transplanting) at substantially lower energy than embodied energy in wasted nitrogen. The state estimation modules show trade-offs, with ViT outperforming RF on phosphorus and calcium estimation ( R 2 0.61 vs 0.58, 0.48 vs 0.35) at higher energy cost. With our modular pipeline, this work opens up opportunities for edge diagnostics and practical opportunities for agricultural sustainability.

Code and data availability

The paper's plant tissue data and vegetation index calculations are stated to be deposited at AgDataCommons but only 'status pending' (not yet public), and images are available only upon request. No authors' public code repository or trained model checkpoint is provided; other URLs are generic libraries/tools.

No evidence-backed public reproduction asset is currently recorded.