摘要
由一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-关于人工智能的最新研究结果已经发表。根据NewsRx记者从大阪大学发回的消息，研究表明：“泰国位于东南亚大陆的心脏地带，与当地和邻国的高生物量燃烧(BB)活动有关。”新闻编辑从大阪大学的研究中得到一句话:“BB的季节模式表现为PM2.5浓度的潜在预测因子。因此,我们将BB因子从社区多尺度空气质量(CMAQ)中分离出来,增强了基于机器学习的PM2.5预测。建立了两个具有不同CMAQ预测因子的光梯度增强机(LightGBM)模型:BB整合模型,这两个模型有共同的控制预测因子，其中包括来自WRF模型的模拟气象变量、人口、海拔和土地利用变量的模拟气象变量，其中包括来自BB(CMAQ_PM25_Othr)以外来源的CMAQ模拟的PM2.5和来自BB排放的CMAQ模拟的PM2.5（CMAQ_PM25_BB）。BB分离模式L优于BB整合模式，总体CV 2值分别为0.86和0.82，特征重要性分析表明CMAQ_PM25_Othr和CMAQ PM25_BB是两个最显著的预测因子。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news originating from Osaka Univers ity by NewsRx correspondents, research stated, "Located in the heart of Mainland Southeast Asia, Thailand is associated with high biomass burning (BB) activitie s from local and neighbouring countries." The news editors obtained a quote from the research from Osaka University: "The seasonal pattern of BB manifests itself as a potential predictor for PM2.5 conce ntration. Consequently, we enhanced machine learning based PM2.5 prediction by s egregating BB factor from the Community Multiscale Air Quality (CMAQ). Two Light Gradient Boosting Machine (LightGBM) models with different CMAQ predictors were developed: the BB-integrated model, which incorporated CMAQ-simulated PM2.5 fro m all emission sources and the BB-segregated model, which incorporated CMAQ-simu lated PM2.5 from sources other than BB (CMAQ_PM25_Othr ) and CMAQ-simulated PM2.5 from BB emissions (CMAQ_PM25_ BB). The two models had shared control predictors, which included simulated mete orological variables from WRF model, population, elevation, and land-use variabl es, and they were evaluated using a crossvalidation (CV). The BB-segregated mode l outperformed the BB-integrated model, achieving overall-CV R2 values of 0.86 a nd 0.82, respectively. The analysis of feature importance for the BB-segregated model indicates that CMAQ_PM25_Othr and CMAQ_ PM25_BB are the two most significant predictors."
NETL
NSTL