A novel approach for time series data forecasting based on ARIMA model for marine fishes

Forecasting of the time series data is a challenge as its details are more complex in nature. Climate change is a global issue as it influences the environment and it impacts directly affecting the human and the marine species. Global warming is a big threat and it reflects in sea temperature. Due to the rising sea temperature, the fishes like sardine and pelagic are not getting the living sea environment and the annual catchment of these fishes are reduced. The fishes are drifted from one place to other. This paper focuses on forecasting these fishes based on the catchment of historical data. The proposed approach incorporates the Multivariate Imputation by Chained Equations (MICE) is used to determine the missing values. The Auto Regressive Integrated Moving Average (ARIMA) model is blended for predicting the upfront values. The proposed approach is tested with various parameters and the test results shows its efficiency.