Crop damage attributed to pest birds is an important problem, particularly in low-income countries. This paper describes a prototype system for pest bird detection using a Conv1D neural network model followed by scaring actions to reduce the presence of pest birds on farms. Acoustic recorders were deployed on farms for data collection, supplemented by acoustic libraries. The sounds of pest bird species were identified and labeled. The labeled data were used in Edge Impulse to train a tinyML Conv1D model to detect birds of interest. The model was deployed on Arduino Nano 33 BLE Sense (nodes) and XIAO (Base station) microcontrollers to detect the pest birds, and based on the detection, scaring sounds were played to deter the birds. The model achieved an accuracy of 96.1% during training and 92.99% during testing. The testing F1 score was 0.94, and the ROC score was 0.99, signifying a good discriminatory ability of the model. The prototype was able to make inferences in 53 ms using only 14.8 k of peak RAM and only 43.8 K of flash memory to store the model. Results from the prototype deployment in the field demonstrated successful detection and triggering actions and SMS messaging notifications. Further development of this novel integrated and sustainable solution will add another tool for dealing with pest birds.

Agricultural pest control traditionally relies on inefficient visual inspections. Acoustic monitoring offers a promising alternative by analyzing pest-specific sounds. While effective, implementing acoustic monitoring in agricultural settings faces practical constraints, particularly the limited computational resources available in remote farming environments. This necessitates optimized machine learning (ML) solutions for low-power edge devices. This study evaluates ML models for bird pest detection on resource-constrained platforms. We evaluated convolutional neural networks (CNNs), recurrent neural networks (RNNs), and traditional ML models by comparing standalone and knowledge-distilled versions of EfficientNetB0 and gated recurrent unity (GRU) against EfficientNetB4, Long short-term memory (LSTM), MobileNetV2, LightGBM, and support vector machine (SVM). Analysis revealed significant performance variations across computational requirements. LightGBM achieved 98% accuracy with minimal resources (8,500 parameters, 7KB, 0.6ms inference), demonstrating good efficiency. SVM (97% accuracy) and distilled GRU (86% accuracy) also showed favorable performance-to-resource ratios. Knowledge distillation substantially enhanced the accuracy of EfficientNetB0 (from 73% to 98%) and modestly improved GRU (from 84% to 86%). We examined platform compatibility across computing tiers, discovering that while high-performance edge devices (Jetson Nano, Raspberry Pi 4) support all studied models effectively, microcontrollers require specialized approaches. Advanced microcontrollers (such as ESP32-S3 and STM32H7) can accommodate optimized implementations, while highly constrained platforms (such as Arduino Nano) require TinyML techniques. This research contributes (i) an on-farm audio dataset, (ii) comprehensive cross-model evaluation metrics, and (iii) deployment optimization strategies for acoustic pest detection systems in resource-constrained agricultural environments.

Monitoring the farm acoustic environment can provide important information about processes affecting crop production. This paper assesses farmers’ knowledge and attitudes toward acoustic technology for farm monitoring in Rwanda. Stratified random sampling was used to select 430 farmers from 3 sectors. Demographic, farm, and technical knowledge data were collected from farmers with a survey. Cross-tabulation results show farmers with secondary and university education are more interested in acoustic technology than those with a primary education and farmers engaged in commercial farming are more interested in technology for monitoring acoustic sources than subsistence farmers. However, nearly all farmers are willing to deploy a listening technology to monitor the acoustic environment. Farmers have a clear priority to listen to animals on the farm, whether they are pests (specifically, birds) or livestock. A chi-square test of independence indicates a significant relationship between farmers’ consideration of technology for farm monitoring and their attitudes toward sound monitoring. Farmers want a technological solution, but demand that the solution be low-cost and provide a simple alert. The results inform system requirements for an Internet of Things acoustic network that can deliver this information to the farmer.