The release of toxic gases by industries, emissions from vehicles, and an increase in the concentration of harmful gases and particulate matter in the atmosphere are all contributing factors to the deterioration of the quality of the air. Factors such as industries, urbanization, population growth, and the increased use of vehicles contribute to the rapid increase in pollution levels, which can adversely impact human health. This paper presents a model for forecasting the air quality index in Nigeria using the Bi-directional LSTM model. The air pollution data was downloaded from an online database (UCL). The dataset was pre-processed using both pandas tools in python. The pre-processed result was used as input features in training a Bi-LSTM model in making future forecasts of the values of the particulate matter Pm2.5, and Pm10. The Bi-LSTM model was evaluated using some evaluation parameters such as mean square error, mean absolute error, absolute mean square, and R^2 square. The result of the Bi-LSTM shows a mean square error of 52.99%, relative mean square error of 7.28%, mean absolute error of 3.4%, and R^2 square of 97%. The model. This shows that the model follows a seamless trend in forecasting the air quality in Port Harcourt, Nigeria.

翻译：工业有毒气体排放、车辆尾气排放以及大气中有害气体和颗粒物浓度的增加，都是导致空气质量恶化的因素。工业化、城镇化、人口增长以及车辆使用频率的上升等因素，使得污染水平迅速升高，对人类健康造成不利影响。本文提出了一种基于双向长短期记忆（Bi-LSTM）模型的尼日利亚空气质量指数预测模型。空气污染数据从在线数据库（UCL）下载，并使用Python中的pandas工具进行预处理。预处理结果作为输入特征，训练Bi-LSTM模型以预测颗粒物PM2.5和PM10的未来值。采用均方误差、平均绝对误差、均方根误差和R²作为评估参数对Bi-LSTM模型进行评价。Bi-LSTM模型的预测结果显示：均方误差为52.99%，相对均方误差为7.28%，平均绝对误差为3.4%，R²达到97%。这表明该模型能够无缝追踪尼日利亚哈科特港空气质量的演变趋势。