Research on the Air Quality Prediction Model of Wuhai Mining Area Based on Deep Learning

本文重点对乌海矿区的空气质量进行了相应的预警研究，并基于过滤后的天气因素构建了深度递归神经网络(DRNN)和深度长短时间记忆神经网络(DLSTM)空气质量预测模型。并对仿真结果进行了比较，发现DLSTM的预测结果优于DRNN，预测精度为92.85%。该模型能够准确预测乌海矿区各种空气污染物浓度的值和趋势。This paper focuses on the air quality early warning research in the Wuhai Mining Area. Based on filtered meteorological factors, we developed two air quality prediction models: Deep Recurrent Neural Network (DRNN) and Deep Long Short-Term Memory Neural Network (DLSTM). By comparing the simulation results, we found that DLSTM outperforms DRNN in prediction, achieving a prediction accuracy of 92.85%. These models can accurately predict the concentrations and trends of various air pollutants in the Wuhai Mining Area.

搜集汇总

背景与挑战

背景概述

该数据集聚焦于乌海矿区的空气质量预警研究，通过构建深度递归神经网络(DRNN)和深度长短时记忆神经网络(DLSTM)模型进行预测。比较结果显示DLSTM模型性能更优，预测精度达到92.85%，能够有效预测空气污染物浓度的数值和变化趋势。