Modeling and implementation of intelligent decision support system for ecological law enforcement based on multi-source environmental data

With the increasing demand of environmental supervision, the research on IDSS (Intelligent Decision Support System) is becoming more and more important. This paper focuses on the system, using satellite remote sensing and Internet of Things equipment to collect multi-source environmental data in a certain area. The data covers the air quality and water quality of ground monitoring stations, the land cover and vegetation index obtained by satellite remote sensing, and the real-time sewage discharge data of enterprise Internet of Things, with a time span of one year. Through data fusion model and intelligent decision-making algorithm model, the data are preprocessed such as cleaning, normalization and feature extraction, and then the algorithm model is used to analyze the data to generate law enforcement decision-making suggestions. Accuracy, recall, F1 value and root mean square error (RMSE) were used to evaluate the model performance. The results show that the accuracy of the improved support vector machine (SVM) model is 93%, and the recall rate is stable at around 91% when the training data is 60%, with F1 value of 92% and RMSE of 0.08. This shows that the improved SVM model has better performance in IDSS of ecological law enforcement and can provide reliable support for law enforcement.