A Machine Learning Approach for Early Detection of Fish Diseases by Analyzing Water Quality

Abstract

Early detection of fish diseases and identifying the underlying causes are crucial for farmers to take necessary steps to mitigate the potential outbreak and thus to avert financial losses with apparent negative implications to the national economy. Typically, fish diseases are caused by viruses and bacteria; according to biochemical studies, the presence of certain bacteria and viruses may affect the level of pH, DO, BOD, COD, TSS, TDS, EC, PO43-, NO3-N, and NH3-N in water, resulting in the death of fishes. Besides, natural processes, e.g., photosynthesis, respiration, and decomposition, also contribute to the alteration of water quality that adversely affects fish health. Being motivated by the recent successes of machine learning techniques, a state-of-art machine learning algorithm has been adopted in this paper to detect and predict the degradation of water quality timely and accurately. Thus, it helps to take preemptive steps against potential fish diseases. The experimental results show high accuracy in detecting fish diseases specific to water quality based on the algorithm with real datasets.

Using machine learning technique for disease outbreak prediction in rainbow trout ( Oncorhynchus mykiss ) farms

“…Researchers can perform data analysis with R‐based ML tools because of the flexibility provided by open source software and libraries, and the detection and modelling of factors causing fish diseases require detailed statistical research (Nayan et al, 2021).…”

Cutting‐edge technologies for detecting and controlling fish diseases: Current status, outlook, and challenges

“…Machine learning techniques may be used to find associations between these factors in historical data. Fish infections caused by protozoans and bacteria have been diagnosed using artificial neural networks (Nayan et al, 2021). In 2020, machine learning was used to evaluate historical shrimp farm data and predict acute hepatopancreatic necrosis disease in shrimp farmed on the east coast of the Mekong Delta of Vietnam (Khiem et al, 2020).…”

“…According to the results of the figures, the suggested method better identifies the RSD‐impacted regions of fish from RSDF photos by labeling them with red pixels (Su et al, 2020). The suggested approach may accurately detect the area affected by RSD in fish by utilizing a standard RGB model to label the afflicted area with red color (red pixels) so that preventive measures can be implemented for survival (Nayan et al, 2021). By evaluating many RSDF photos, the proposed method can be deemed a better way of identifying RSD areas in fish.…”

Smart Prediction of Water Quality System for Aquaculture using Machine Learning Algorithms

“…A. A. Nayan et al has worked on River water quality for agriculture and fishing application [4] and identified fish diseases due to the changes in water quality [5] using Machine learning. He measured the water quality in terms of pH, DO, BOD, COD, TSS, TDS, EC, PO43-, NO3-N, and NH3-N and predicted the output using boosting technique.…”