Iot Based Smart Biofloc Monitoring System For Fish Farming Using Machine Learning

Abstract

Biofloc Technology Has Emerged As A Sustainable And Space-efficient Method For Fish Farming, Particularly Valuable In Regions With Limited Water Resources. However, Its Operation Is Highly Sensitive To Variations In Water Quality Parameters Such As PH, Total Dissolved Solids (TDS), Ammonia Levels, Turbidity, And Temperature. This Paper Presents A Cost-effective, Solar-powered Internet Of Things (IoT)-based Biofloc Monitoring System Integrated With Machine Learning (ML) Techniques To Detect Early Signs Of Fish Mortality In Aquaculture Tanks. Designed For Low-income Fish Farmers In Southern Punjab, Pakistan, The System Continuously Measures Critical Water Quality Parameters Using Affordable Sensors Connected To Arduino UNO And NodeMCU ESP8266 Microcontrollers. Over A Period Of 1.5 Months, Data Was Collected At Two-minute Intervals And Uploaded To The ThingSpeak Cloud Platform. After Preprocessing And Balancing The Dataset Using ADASYN, Several ML Algorithms—including Random Forest, XGBoost, Decision Trees, Support Vector Machines, And Naïve Bayes—were Trained And Evaluated. The Random Forest And XGBoost Classifiers Outperformed Others, Achieving Up To 98% Accuracy In Predicting Fish Mortality. This System Not Only Enhances Operational Efficiency In Biofloc Fish Farming But Also Reduces Fish Mortality And Economic Losses By Issuing Timely Warnings. The Results Demonstrate The Potential Of IoT-ML Integration In Transforming Small-scale Aquaculture Into A More Data- Driven And Sustainable Practice.

Keywords