Classification of Sentinel-2 satellite imagery in Iran for geological purposes using deep convolutional neural networks: a case study for soil type identification

Mostafa Kiani Shahvandi¹

Abstract :
In this paper, Sentinel-2 satellite imagery is used for the classification of different soil types using the method of deep convolutional neural networks. Role of the presence of different phenomena in the image, including clouds, on the accuracy of the classification is analyzed. Two case studies are presented for Iran. In the first study, a region is chosen that is approximately consisted of one main type of soil, without any other type of phenomena. It is shown that the overall classification accuracy is around 95 percent, with k=0.889 . In the second study, however, the region is mixed: there are different soil types, but there are other phenomena present as well, including large clouds. The overall accuracy of classification in this case is lower, compared to the first case, being around 92 percent and with k=0.854.

Keywords : deep convolutional neural networks sentinel 2 soil type satellite imagery

---

زبان مقاله : انگلیسی
محور مقاله : علوم مهندسی
محل انتشار : دومین کنگره بین المللی علوم و مهندسی - پاریس
آدرس وب سایت کنفرانس : parisconf.com
کد IOI مقاله : XCAZ-EFBDC
لینک مستقیم مقاله : https://isnac.ir/XCAZ-EFBDC
نمایش چکیده فارسی : https://isnac.ir/SA/XCAZ-EFBDC

سایر مقالات ارائه دهنده

1. Image Gravimetry: A New Remote Sensing Approach for Gravity Analysis in Geophysics
2. Identification and Classification of Phenomena in Multispectral Satellite Imagery Using a New Image Smoother Method and its Applications in Environmental Remote Sensing
3. Classification of Sentinel-2 satellite imagery in Iran for geological purposes using deep convolutional neural networks: a case study for soil type identification
4. Accuracy assessment of crop classification in hyperspectral imagery using very deep convolutional neural networks

سایر مقالات محل انتشار

1. Radioactive wastewater and solutions: an Important challenge for humans and environment
2. Infinite Universes, Pshi Unit & Goopn Hypothesis
3. Analysis of weight on bit on torsional stick/slip vibration of drill string
4. بررسی آرای ترافعی دیوان بین المللی دادگستری درتوسعه حقوق بشر
5. نگاه کلی مدیریت یکپارچه شهری با ابعاد زیست محیطی و نقش آموزش فناوری اطلاعات در کاهش چالش زیست محیطی با تاکید بر توسعه پایداری شهری
6. طراحی مجتمع مسکونی با رویکرد صفر انرژی ZEB و تکیه بر سامانه های غیر فعال خورشیدی
7. Reinforcing building adobe by Laser Shock technology and thermal retrofitting
8. بررسی تأثیر فاکتورهای سبک بخشودگی برشادکامی زنان متأهل دانشجو
9. مدیریت پسماند و تولید بیوگاز
10. Classification of Sentinel-2 satellite imagery in Iran for geological purposes using deep convolutional neural networks: a case study for soil type identification
11. بررسی و ارزیابی رسوب آسفالتین در مخازن نفتی
12. The Effect of a Nasm Method (American Academy of Sports Medicin )Range of genu varum in Players of the Paleolithic team in Tabriz city
13. Preparation of 6-mercaptopurine Imprinted hydrophilic Nanospheres as Novel Drug Delivery System
14. ساخت کرم سلولی ضد آفتاب گیاهی با استفاده از سرم خون انسانی
15. Synthesis of molecularly imprinted polymers for the application of selective Vindesine as Novel Drug Delivery System