# Edge-Based Standing-Water Detection via FSM-Guided Tiering and Multi-Model Consensus

arXiv: https://arxiv.org/abs/2604.03308 · HTML: https://mlsanity.com/paper/2604.03308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 20 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 1 of 1)

- [An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal Imaging](https://mlsanity.com/paper/2411.03835/) (2024)

## Built on by (most cited first, 1 of 1)

- [Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods](https://mlsanity.com/paper/2607.17774/) (2026)

## Abstract (arXiv)

Standing water in agricultural fields threatens vehicle mobility and crop health. This paper presents a deployed edge architecture for standing-water detection using Raspberry-Pi-class devices with optional Jetson acceleration. Camera input and environmental sensors (humidity, pressure, temperature) are combined in a finite-state machine (FSM) that acts as the architectural decision engine. The FSM-guided control plane selects between local and offloaded inference tiers, trading accuracy, latency, and energy under intermittent connectivity and motion-dependent compute budgets. A multi-model YOLO ensemble provides image scores, while diurnal-baseline sensor fusion adjusts caution using environmental anomalies. All decisions are logged per frame, enabling bit-identical hardware-in-the-loop replays. Across ten configurations and sensor variants on identical field sequences with frame-level ground truth, we show that the combination of adaptive tiering, multi-model consensus, and diurnal sensor fusion improves flood-detection performance over static local baselines, uses less energy than a naive always-heavy offload policy, and maintains bounded tail latency in a real agricultural setting.