Smart aquaponics: An innovative machine learning framework for fish farming optimization

This study presents an innovative approach to aquaponics by integrating artificial intelligence (AI). The system addresses sustainability challenges by utilizing a novel approach to machine learning to create a fully sustainable system that improves nutrition and fish growth in aquaponics. The study focuses on predicting the length and weight of fish species by analyzing different environmental parameters, including pH, ammonia, and nitrate levels. Data preprocessing integrates nearest-neighbor interpolation and feature standardization to ensure quality and consistency. The light gradient-boosting machine (LightGBM) machine learning model, optimized by five-fold cross-validation, emerges as the superior predictor. Moreover, a novel aspect of the study is the integration of local interpretable model-agnostic explanations (LIME) for enhanced model transparency. The outcome helps to understand the impacts of individual characteristics on the predictions. External validation using different data reaffirms the models' generalizability. Hence, the integration of renewable energy, artificial intelligence, and rigorous analysis shows the potential to improve sustainable agriculture, paving the way for efficient and environmentally conscious indoor farming practices. However, the main framework of this study has the advantage of replicating other fish species using a new set of parameters.

Other Information

Published in: Computers and Electrical Engineering
License: http://creativecommons.org/licenses/by/4.0/
See article on publisher's website: https://dx.doi.org/10.1016/j.compeleceng.2024.109590