摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据NewsRx记者从中华人民共和国哈尔滨发回的消息，研究表明：“卫星遥感在探测森林火灾烟气方面发挥着重要作用。然而，现有的基于遥感图像的森林火灾烟气探测方法仅仅依赖于图像提供的信息，查看火灾中火点的位置信息和亮温。本文从东北林业大学的研究中得到一句话:“这种疏忽大大增加了误判烟雾羽的概率。本文提出了一种烟雾探测模型Forest smoke-Fire N et(FSF Net),该模型将野火烟雾图像与该地区的动态亮温信息结合起来,利用中分辨率成像光谱仪R(MODIS)构建了MODIS_smoke_FPT数据集。利用火灾现场的气象信息和高程数据确定烟雾位置和野火亮温阈值D，利用数据集提供的图像数据和火点面积数据分别训练深度学习和机器学习模型，并利用度量图对深度学习模型的性能进行评价。采用均方根Erro R(RMSE)和平均绝对误差(MAE)评价机器学习的回归性能，将所选机器学习模型与深度L学习模型有机地结合起来。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on artificial intelligence are presented in a new report. According to news originating from Harbin, People ’s Republic of China, by NewsRx correspondents, research stated, “Satellite remo te sensing plays a significant role in the detection of smoke from forest fires. However, existing methods for detecting smoke from forest fires based on remote sensing images rely solely on the information provided by the images, overlooki ng the positional information and brightness temperature of the fire spots in fo rest fires.” Our news journalists obtained a quote from the research from Northeast Forestry University: “This oversight significantly increases the probability of misjudgin g smoke plumes. This paper proposes a smoke detection model, Forest Smoke-Fire N et (FSF Net), which integrates wildfire smoke images with the dynamic brightness temperature information of the region. The MODIS_Smoke_ FPT dataset was constructed using a Moderate Resolution Imaging Spectroradiomete r (MODIS), the meteorological information at the site of the fire, and elevation data to determine the location of smoke and the brightness temperature threshol d for wildfires. Deep learning and machine learning models were trained separate ly using the image data and fire spot area data provided by the dataset. The per formance of the deep learning model was evaluated using metric MAP, while the re gression performance of machine learning was assessed with Root Mean Square Erro r (RMSE) and Mean Absolute Error (MAE). The selected machine learning and deep l earning models were organically integrated.”
NETL
NSTL