Affordable Precision Agriculture: A Deployment-Oriented Review of Low-Cost, Low-Power Edge AI and TinyML for Resource-Constrained Farming Systems
Organizations: Techno India University, Salt Lake, West Bengal, India · Sister Nivedita University, Newtown, West Bengal, India
Abstract
Precision agriculture increasingly integrates artificial intelligence to enhance crop monitoring, irrigation management, and resource efficiency. Nevertheless, the vast majority of the current systems are still mostly cloud-based and require reliable connectivity, which hampers the adoption to smaller scale, smallholder farming and underdeveloped country systems. Using recent literature reviews, ranging from 2023 to 2026, this review covers deployments of Edge AI, focused on the evolution and acceptance of Tiny Machine Learning, in low-cost and low-powered agriculture. A hardware-targeted deployment-oriented study has shown pronounced variation in architecture with microcontroller-class platforms i.e. ESP32, STM32, ATMega dominating the inference options, in parallel with single-board computers and UAV-assisted solutions. Quantitative synthesis shows quantization is the dominant optimization strategy; the approach in many works identified: around 50% of such works are quantized, while structured pruning, multi-objective compression and hardware aware neural architecture search are relatively under-researched. Also, resource profiling practices are not uniform: while model size is occasionally reported, explicit flash, RAM, MAC, latency and millijoule level energy metrics are not well documented, hampering reproducibility and cross-system comparison. Moreoever, to bridge the gap between research prototypes and deployment-ready systems, the review also presents a literature-informed deployment perspective in the form of a privacy-preserving layered Edge AI architecture for agriculture, synthesizing the key system-level design insights emerging from the surveyed works. Overall, the findings demonstrate a clear architectural shift toward localized inference with centralized training asymmetry.
Figures & tables
| Review | Scope | TinyML Focus | Hardware Profiling | Energy/Resource Metrics | Deployment Orientation | Time Range |
|---|---|---|---|---|---|---|
| Ahmed & Shakoor ( 2025 ) | IoT, Big Data, AI in agriculture | No | Limited | No | Survey-level | Broad |
| Gauttam et al. ( 2026a ) | Edge computing in smart agriculture | Partial | Partial | No | Architectural | 2020–2025 |
| Heydari & Mahmoud ( 2025a ) | TinyML applications survey | Yes | General | Limited | Application-level | Broad |
| Paul et al. ( 2025 ) | Deep learning for plant stress detection | No | No | No | Algorithm-centric | Broad |
| Madiwal et al. ( 2025 ) | Edge AI and IoT for crop disease | Partial | Limited | No | Survey-level | Recent |
| Singh & Gill ( 2023b ) | General survey on Edge AI | No | General | No | Taxonomic | Broad |
| Application | References | Hardware | Model | Optimization | Key Metric | Offline |
|---|---|---|---|---|---|---|
| Plant Disease Detection | Samanta et al. (2025b) | ESP32-CAM | CNN | Quantization | 92% Acc. | Yes |
| Koli et al. (2025) | Edge Device | DS-CNN | Lightweight Arch. | 96% Acc. | Yes | |
| Gookyi et al. (2024) | Arduino BLE 33 | CNN | Augmentation + Tuning | 94.6%, 7.6 ms | Yes | |
| Annadata et al. (2025) | ESP-EYE 32 | CNN | Path Optimization | 90% Acc. | Yes | |
| Tao et al. (2025) | LoRa + Edge | CNN | Adaptive Offloading | – | Partial | |
| Kouzinopoulos and Manna (2025) | STM32U575 | YOLOv8n | Pruning + INT8 | 51.8 mJ/inf. | Yes |
| References | Intelligence Distribution | Edge–Cloud Dependency | Communication Layer | Inference / Training Tier |
|---|---|---|---|---|
| Samanta et al. (2025b) | Fully On-Device | None | Not Specified | On-Device Inference / Cloud Training |
| Tao et al. (2025) | Edge-Assisted | Optional | LoRa + IoT Network | Hybrid Inference / Cloud Training |
| Thirumalaiah et al. (2025) | Edge-Coordinated | Optional | LoRa | Edge Inference / Cloud Training |
| Soltani et al. (2025) | Distributed Collaborative | Required | Wireless Edge Link | Edge Inference / Distributed Training |
| Bhattacharya and Pandey (2024) | Edge-Assisted | Optional | IoT Network | Node Inference / Cloud Training |
| Annadata et al. (2025) | Fully On-Device | None | UAV Internal Control | On-Device Inference / Cloud Training |
| References | Quant. | Pruning | Model Comp. | Transfer Learning | Split Learning | DVFS | Adaptive Offloading | Lightweight Arch. |
|---|---|---|---|---|---|---|---|---|
| Samanta et al. (2025b) | Yes | – | – | – | – | – | – | Yes |
| Koli et al. (2025) | Yes | – | Yes | – | – | – | – | Yes |
| Gookyi et al. (2024) | – | – | – | – | – | – | – | Yes |
| Tao et al. (2025) | – | – | – | – | – | – | Yes | Yes |
| Kouzinopoulos and Manna (2025) | Yes | Yes | – | – | – | – | – | Yes |
| Madiwal et al. (2025) | Yes | – | – | – | – | – | – | Yes |
| References | Flash / ROM | RAM | Model Size | Latency | Energy / Inference |
|---|---|---|---|---|---|
| Gookyi et al. (2024) | 344.7 KB | 726.6 KB | CNN-MDD | 7.6 ms | – |
| Kouzinopoulos and Manna (2025) | 100 KB | – | INT8 YOLOv8n | – | 51.8 mJ |
| Hernandez-Hidalgo et al. (2026) | – | – | 6.2 KB Model | – | – |
| Baishya and Dutta (2025) | – | – | 99% Size Reduction | – | – |
| Bhattacharya and Pandey (2024) | – | – | – | – | 8.5% Energy |
| Soltani et al. (2025) | – | – | – | – | 86% Energy |
Edge ML
Edge machine learning runs and adapts models on nearby devices to reduce latency, bandwidth use, and exposure of sensitive data.
See all 129 papers