Kato, Soushi

The potential of shortwave infrared (SWIR) remote sensing to detect hotspots has been investigated using satellite data for decades. The hotspots detected by satellite SWIR sensors include very high-temperature heat sources such as wildfires, volcanoes, industrial activity, or open burning. This study proposes an automated classification method of heat source detected utilizing Landsat 8 and Sentinel-2 data. We created training data of heat sources via visual inspection of hotspots detected by Landsat 8. A scheme to classify heat sources for daytime data was developed by combining classification methods based on a Convolutional Neural Network (CNN) algorithm utilizing spatial features and a decision tree algorithm based on thematic land-cover information and our time series detection record. Validation work using 10,959 classification results corresponding to hotspots acquired from May 2017 to July 2019 indicated that the two classification results were in 79.7% agreement. For hotspots where the two classification schemes agreed, the classification was 97.9% accurate. Even when the results of the two classification schemes conflicted, either was correct in 73% of the samples. To improve the accuracy, the heat source category was re-allocated to the most probable category corresponding to the combination of the results from the two methods. Integrating the two approaches achieved an overall accuracy of 92.8%. In contrast, the overall accuracy for heat source classification during nighttime reached 79.3% because only the decision tree-based classification was applicable to limited available data. Comparison with the Visible Infrared Imaging Radiometer Suite (VIIRS) fire product revealed that, despite the limited data acquisition frequency of Landsat 8, regional tendencies in hotspot occurrence were qualitatively appropriate for an annual period on a global scale.

Hot spot detection and retrieval of brightness temperature with satellites operating in NIR-SWIR, is traditionally optimized for night data. However, if the radiance from hotspot could be distinguished from the reflected solar radiance the method could be valid for day time (Kato et al 2016). This is the idea at the base of the Landsat 8/Sentinel-2 Hotspot Detection System (Hotarea) which automatically detects hotspots (e.g., fires and volcanoes) in Landsat 8 - released from U. S. Geological Survey (USGS) and Sentinel-2 data - released by d European Space Agency (ESA) and displays the results on a web-based GIS system. The Hotarea experimentally displays the heat sources classified based on two distinct methods, namely the deep learning and empirical classifier based on land cover and detection history. There are 5 hot spot categories including volcano, fire, factory, oil platform, roof reflection and 1 unknown. To reduce the number of false attributions and to identify the unknown, an extended work of validation is required. We present the validation activity carried out within the Free Research project titled " Testing Japan hot spot system for HTE in central Italy".- FIRS, funded by MIUR which focused on testing the Hotarea detection system over Marche Umbria Lazio and Toscana (M U L T) Italian regions.