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

## TL;DR

This paper introduces a modular system for real-time nutrient monitoring in agriculture, balancing efficiency and accuracy to reduce waste and improve sustainability.

## Contribution

A novel tiered pipeline for lightweight anomaly detection and nutrient estimation using multispectral imaging and machine learning.

## Key findings

- Anomaly detection achieved 73% accuracy for low-fertilizer samples with low energy use.
- Vision transformers outperformed random forests in estimating phosphorus and calcium.
- The system enables edge deployment for sustainable nutrient management.

## 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.