Chi Yufeng, Wu Yingying, Wang Kai, Ren Yin, Ye Hong, Yang Shuiqiao, Lin Guanjun
School of Information Engineering, Sanming University, Sanming, 365004, China.
Chinese Language and Literature Specialty, Sanming University, Sanming, 365004, China.
J Environ Manage. 2024 Nov;370:122725. doi: 10.1016/j.jenvman.2024.122725. Epub 2024 Oct 2.
The short-term risks associated with atmospheric trace gases, particularly carbon monoxide (CO), are critical for ecological security and human health. Traditional statistical methods, which still dominate the assessment of these risks, limit the potential for enhanced accuracy and reliability. This study evaluates the performance of traditional models (ARIMA), machine learning models (LightGBM, ConvLSTM2D), and optimized machine learning solutions (Bayes residual optimization ConvLSTM2D LightGBM, Bayes_CL) in predicting Sentinel 5P columnar CO levels. This study findings demonstrate that machine learning models and their optimized versions significantly outperform traditional ARIMA models in cross-validation (CV), visualization, and overall prediction performance. Notably, machine learning model based on Bayes and residual optimization (Bayes_CL) achieved the highest CV score (Bayes_CL R = 0.8, LightGBM R = 0.79, ConvLSTM2D R = 0.75, ARIMA R = 0.61), along with superior visualization and other metrics. Using Bayes_CL, we effectively quantified a 2.4% increase in columnar CO levels in mainland China in the second half of 2023, following the complete lifting of COVID-19 lockdowns. This study confirms that machine learning models can effectively replace traditional methods for short-term risk assessment of Sentinel 5P columnar CO. This transition holds significant implications for policy formulation, greenhouse effect assessment, and population health risk evaluation, especially in uncertain situations where human activities are severely disrupted, thereby affecting environmental safety.
与大气痕量气体，特别是一氧化碳（CO）相关的短期风险对生态安全和人类健康至关重要。传统统计方法在这些风险评估中仍占主导地位，限制了提高准确性和可靠性的潜力。本研究评估了传统模型（ARIMA）、机器学习模型（LightGBM、ConvLSTM2D）以及优化的机器学习解决方案（贝叶斯残差优化ConvLSTM2D LightGBM，Bayes_CL）在预测哨兵5P柱状CO水平方面的性能。本研究结果表明，机器学习模型及其优化版本在交叉验证（CV）、可视化和整体预测性能方面显著优于传统ARIMA模型。值得注意的是，基于贝叶斯和残差优化的机器学习模型（Bayes_CL）获得了最高的CV分数（Bayes_CL R = 0.8，LightGBM R = 0.79，ConvLSTM2D R = 0.75，ARIMA R = 0.61），同时具有出色的可视化效果和其他指标。使用Bayes_CL，我们有效地量化了2023年下半年中国内地在新冠疫情封锁全面解除后柱状CO水平上升了2.4%。本研究证实，机器学习模型可以有效地取代传统方法用于哨兵5P柱状CO的短期风险评估。这一转变对政策制定、温室效应评估和人群健康风险评估具有重要意义，特别是在人类活动受到严重干扰从而影响环境安全的不确定情况下。
