Year: 2026
Type: article
Abstract: Smart farming depends on Internet of Things (IoT) sensors that report temperature, humidity, soil moisture and light intensity around the clock. When these sensors fail or their readings are corrupted, automated decisions such as irrigation and climate control can waste resources and reduce yield. Threshold rules and classical machine learning methods struggle with the daily and seasonal cycles found in farm data, and they often raise too many false alarms. This study develops and tests a hybrid 1D Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) model for anomaly detection in agricultural IoT systems.
Institution: Nile University of Nigeria
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
Funder: Nile University
OpenAlex ID: W7237273993
