Identification of Logged and Windthrow Areas from Sentinel-2 Satellite Images Using the U-Net Convolutional Neural Network and Factors Affecting Its Accuracy
A. I. Kanev, A. V. Tarasov, A. N. Shikhov, N. S. Podoprigorova, F. A. Safonov
{"title":"Identification of Logged and Windthrow Areas from Sentinel-2 Satellite Images Using the U-Net Convolutional Neural Network and Factors Affecting Its Accuracy","authors":"A. I. Kanev, A. V. Tarasov, A. N. Shikhov, N. S. Podoprigorova, F. A. Safonov","doi":"10.1134/s0010952523700569","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The results of detection (segmentation) of forest disturbances (logged and windthrow areas) based on <i>Sentinel-2</i> satellite images with convolutional neural networks of U-net architecture in different regions of the European territory of Russia and the Urals are presented. The volume of the training sample was over 17 thousand objects. Overall, both logged and windthrow areas are detected with satisfactory accuracy (the average F-measure is over 0.5). At the same time, substantial differences in detection accuracy were found depending on the characteristics of both disturbances themselves and the affected forest cover. Thus, the maximum accuracy was achieved for tornado-induced windthrow areas, due to their geometric features. The dependence of windthrow detection accuracy on the species composition of damaged forests is not obvious and requires clarification; at the same time, the average area of damaged forest sites has a substantial effect on it. The maximum F-measure calculated for logged areas detected on test pairs of <i>Sentinel-2</i> images reaches 0.80, which is substantially higher than in previously published studies with the U-net model. The maximum accuracy is typical for large clear-cuts in mixed and dark coniferous forests, while selective logged areas in deciduous forests are characterized by lowest one. The accuracy for wintertime and summertime pairs of images is substantially higher than for multiseasonal pairs. Also, the accuracy strongly varies for different types of logged areas. Thus, forest roads on summertime images are detected with the lowest producer’s accuracy, while logged areas on wintertime images are detected with highest one.</p>","PeriodicalId":56319,"journal":{"name":"Cosmic Research","volume":"3 1","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cosmic Research","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1134/s0010952523700569","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
The results of detection (segmentation) of forest disturbances (logged and windthrow areas) based on Sentinel-2 satellite images with convolutional neural networks of U-net architecture in different regions of the European territory of Russia and the Urals are presented. The volume of the training sample was over 17 thousand objects. Overall, both logged and windthrow areas are detected with satisfactory accuracy (the average F-measure is over 0.5). At the same time, substantial differences in detection accuracy were found depending on the characteristics of both disturbances themselves and the affected forest cover. Thus, the maximum accuracy was achieved for tornado-induced windthrow areas, due to their geometric features. The dependence of windthrow detection accuracy on the species composition of damaged forests is not obvious and requires clarification; at the same time, the average area of damaged forest sites has a substantial effect on it. The maximum F-measure calculated for logged areas detected on test pairs of Sentinel-2 images reaches 0.80, which is substantially higher than in previously published studies with the U-net model. The maximum accuracy is typical for large clear-cuts in mixed and dark coniferous forests, while selective logged areas in deciduous forests are characterized by lowest one. The accuracy for wintertime and summertime pairs of images is substantially higher than for multiseasonal pairs. Also, the accuracy strongly varies for different types of logged areas. Thus, forest roads on summertime images are detected with the lowest producer’s accuracy, while logged areas on wintertime images are detected with highest one.
摘要 介绍了基于哨兵-2 卫星图像的 U 型卷积神经网络在俄罗斯欧洲领土和乌拉尔不同地区对森林干扰（伐木区和风刮区）的检测（分割）结果。训练样本的数量超过 1.7 万个。总体而言，伐木区和风蚀区的检测精度令人满意（平均 F 值超过 0.5）。同时，由于干扰本身和受影响森林植被的特征不同，检测精度也存在很大差异。因此，龙卷风引起的风切变区域由于其几何特征而达到了最高精度。风切变检测精度与受损森林物种组成的关系并不明显，需要加以澄清；同时，受损森林地点的平均面积对其也有很大影响。对哨兵-2 图像测试对中检测到的伐木区计算出的最大 F 测量值达到 0.80，大大高于之前发表的使用 U 网模型的研究结果。针阔混交林和暗针叶林中的大面积伐木区的准确度最高，而落叶林中的选择性伐木区的准确度最低。冬季和夏季图像对的准确率远远高于多季节图像对。此外，不同类型采伐区的准确度也有很大差异。因此，夏季图像上的森林道路检测精度最低，而冬季图像上的伐木区检测精度最高。
期刊介绍：
Cosmic Research publishes scientific papers covering all subjects of space science and technology, including the following: ballistics, flight dynamics of the Earth’s artificial satellites and automatic interplanetary stations; problems of transatmospheric descent; design and structure of spacecraft and scientific research instrumentation; life support systems and radiation safety of manned spacecrafts; exploration of the Earth from Space; exploration of near space; exploration of the Sun, planets, secondary planets, and interplanetary medium; exploration of stars, nebulae, interstellar medium, galaxies, and quasars from spacecraft; and various astrophysical problems related to space exploration. A chronicle of scientific events and other notices concerning the main topics of the journal are also presented.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
