Microorganism estimation in a shrimp pond using Gaussian process regressor and gradient tree boosting

Abstract

The balance of the aquatic ecosystem is an influential factor in the world of aquaculture, especially in shrimp cultivation. The one that plays a role in that ecosystem is aquatic microorganisms such as vibrio, bacteria, and algae. Therefore, farmers need to know their number and ratio to maintain the shrimp growth. Thus, in this research, models that can estimate vibrio-bacteria ratio and number of algae are developed. These models are formed from aquaculture datasets which are modeled using machine learning algorithms named Gaussian process regressor (GPR) and gradient tree boosting (GTB). Other processing techniques like data pre-processing, feature decomposition, and optimization are also applied to improve model performance. Moreover, these models are also compared to other models which are modeled using another machine learning algorithm like support vector regression (SVR), Lasso, and kernel ridge regression (KRR), so that the best models can be determined. Based on k-fold cross-validation, the GPR model has the best performance in estimating the vibrio-bacteria ratio with mean absolute error (MAE) value of 0.02482 and explained variance score of 0.96515. Then, in the algae estimation, the best performance is achieved by the GTB model with MAE value of 6.55554 and explained variance score of 0.33001.