The Use of Geospatial AI for Remote Sensing Image Classification
DOI:
https://doi.org/10.52575/2712-7443-2024-48-4-526-541Keywords:
geospatial artificial intelligence, remote sensing, machine learning, segmentation, classificationAbstract
In recent years, geospatial artificial intelligence has become an integral tool in the analysis and interpretation of remote sensing images. This work explores the application of geospatial artificial intelligence methods for effective classification of remote sensing images. Traditional image processing approaches often face limitations related to object state variability, data quality, and information volume. The use of machine learning and deep learning algorithms allows overcoming these obstacles, providing more accurate and reliable results. For the classification of spatial objects, Sentinel-2 satellite images of the areas used by the Novosibirsk region farms taken from May to April were used, with a spatial resolution of 10 m per pixel. Image segmentation was performed using SAGA GIS software. For machine learning, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP) methods were used. Among all models, MLP showed the best results with the accuracy of 95.20 % and a high Cohen's Kappa coefficient, while RF and XGBoost models showed 85.0 %. This makes the MLP model an optimal choice, especially when a high classification accuracy is important.
Downloads
References
Список литературы
Асмус В.В., Бучнев А.А., Кровотынцев В.А., Пяткин В.П., Салов Г.И. 2018. Комплекс программного обеспечения PlanetaMonitoring в прикладных задачах дистанционного зондирования. Автометрия, 54(3): 14–23. https://doi.org/10.15372/AUT20180302.
Гарафутдинова Л.В., Каличкин В.К., Федоров Д.С. 2024. Объектно ориентированная классификация изображений дистанционного зондирования Земли с использованием машинного обучения. Вестник НГАУ (Новосибирский государственный аграрный университет), 2: 37–47. https://doi.org/10.31677/2072-6724-2024-71-2-37-47.
Колесников А.А. 2022. Анализ методов и средств искусственного интеллекта для анализа и интерпретации данных активного дистанционного зондирования. Вестник СГУГиТ (Сибирского государственного университета геосистем и технологий), 27(3): 74–94. https://doi.org/10.33764/2411-1759-2022-27-3-74-94.
Фомина Е.С. 2023. Оценка эффективности применения специализированных нейронных сетей для повышения разрешения изображений, получаемых при дистанционном зондировании Земли. Системы управления, связи и безопасности, 3: 71–90. https://doi.org/10.24412/2410-9916-2023-3-71-90.
Якушев В.П., Захарян Ю.Г., Блохина С.Ю. 2022. Состояние и перспективы использования дистанционного зондирования Земли в сельском хозяйстве. Современные проблемы дистанционного зондирования Земли из космоса, 19(1): 287–294. https://doi.org/10.21046/2070-7401-2022-19-1-287-294.
Alom M.Z., Taha T.M., Yakopcic Ch., Westberg S., Sidike P., Nasrin M.S., Hasan M., Van Essen B.C., Awwal A.A.S., Asari V.K. 2019. A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics, 8(3): 292. https://doi.org/10.3390/electronics8030292.
Adugna T., Xu W., Fan J. 2022. Comparison of Random Forest and Support Vector Machine Classifiers for Regional Land Cover Mapping Using Coarse Resolution FY-3C Images. Remote Sensing, 14(3): 574. https://doi.org/10.3390/rs14030574.
Basheer S., Wang X., Farooque A.A., Nawaz R.A., Liu K., Adekanmbi T., Liu S. 2022. Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sensing, 14(19): 4978. https://doi.org/10.3390/rs14194978.
Breiman L. 2001. Random Forests. Machine Learning, 45: 5–32. https://doi.org/10.1023/A:1010933404324.
Carabantes M. 2020. Black-Box Artificial Intelligence: an Epistemological and Critical Analysis. AI & Society, 35: 309–317. https://doi.org/10.1007/s00146-019-00888-w.
Chen T., Guestrin C. 2016. Xgboost: A Scalable Tree Boosting System. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785–794. https://doi.org/10.1145/2939672.2939785.
Chen G., Weng Q., Hay G.J., He Y. 2018. Geographic Object-Based Image Analysis (GEOBIA): Emerging Trends and Future Opportunities. GIScience & Remote Sensing, 55(2): 159–182. https://doi.org/10.1080/15481603.2018.1426092.
Choi Y. 2023. GeoAI: Integration of Artificial Intelligence, Machine Learning, and Deep Learning with GIS. Applied Sciences, 13(6): 3895. https://doi.org/10.3390/app13063895.
Ekeanyanwu C.V., Obisakin I.F., Aduwenye P., Dede-Bamfo N. 2022. Merging GIS and Machine Learning Techniques: A Paper Review. Journal of Geoscience and Environment Protection, 10(9): 61–83. https://doi.org/10.4236/gep.2022.109004.
Ezzahouani B., Teodoro A., Kharki O.El., Jianhua L., Kotaridis I., Yuan X., Ma L. 2023. Remote Sensing Imagery Segmentation in Object-Based Analysis: A Review of Methods, Optimization, and Quality Evaluation Over the Past 20 years. Remote Sensing Applications: Society and Environment, 32: 101031. https://doi.org/10.1016/j.rsase.2023.101031.
Hossain M.D., Chen D. 2019. Segmentation for Object-Based Image Analysis (OBIA): A Review of Algorithms and Challenges from Remote Sensing Perspective. ISPRS Journal of Photogrammetry and Remote Sensing, 150: 115–134 р. https://doi.org/10.1016/j.isprsjprs.2019.02.009.
Janga B., Asamani G.P., Sun Z., Cristea N. 2023. A Review of Practical AI for Remote Sensing in Earth Sciences. Remote Sensing, 15(16): 4112. https://doi.org/10.3390/rs15164112.
Johnson B.A., Ma L. 2020. Image Segmentation and Object-Based Image Analysis for Environmental Monitoring: Recent Areas of Interest, Researchers’ Views on the Future Priorities. Remote Sensing, 12(11): 1772. https://doi.org/10.3390/rs12111772.
Li W., Hsu C.-Y. 2022. GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography. ISPRS International Journal of Geo-Information, 11(7): 385. https://doi.org/10.3390/ijgi11070385.
Mehmood M., Shahzad A., Zafar B., Shabbir A., Ali N. 2022. Remote Sensing Image Classi-Fication: A Comprehensive Review and Applications. Mathematical Problems in Engineering, 1: 5880959. https://doi.org/10.1155/2022/5880959.
Nalluri M., Pentela M., Eluri N.R. 2020. A Scalable Tree Boosting System: XG Boost. International Journal of Research Studies in Science, Engineering and Technology, 7(12): 36–51. https://doi.org/10.22259/2349-476X.0712005.
Radočaj D., Jurišić M. 2022. GIS-Based Cropland Suitability Prediction Using Machine Learning: A Novel Approach to Sustainable Agricultural Production. Agronomy, 12(9): 2210. https://doi.org/10.3390/agronomy12092210.
Sagan V., Coral R., Bhadra S., Alifu H., Al Akkad O., Giri A., Esposito F. 2024. Hyperfidelis: A Software Toolkit to Empower Precision Agriculture with GeoAI. Remote Sensing, 16(9): 1584. https://doi.org/10.3390/rs16091584.
Vali A., Comai S., Matteucci M. 2020. Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review. Remote Sensing, 12(15): 2495. https://doi.org/10.3390/rs12152495
Zhang Y., Liu J., Shen W. 2022. A Review of Ensemble Learning Algorithms Used in Remote Sensing Applications. Applied Sciences, 12(17): 8654. https://doi.org/10.3390/app12178654.
Zapf A., Castell S., Morawietz L., Karch A. 2016. Measuring Inter-Rater Reliability for Nominal Data – which Coefficients and Confidence Intervals are Appropriate? BMC Medical Research Methodology, 16: 1–10. https://doi.org/10.1186/s12874-016-0200-9.
References
Asmus V.V., Buchnev A.A., Krovotyntsev V.A., Pyatkin V.P., Salov G.I. 2018. Planetamonitoring Software Complex in Applied Remote Sensing Problems. Optoelectronics, Instrumentation and Data Processing, 54(3): 222–229 (in Russian). https://doi.org/10.3103/S8756699018030020
Garafutdinova L.V., Kalichkin V.K., Fedorov D.S. 2024. Object-Oriented Classification of Remote Sensing Earth Images Using Machine. Bulletin of NSAU (Novosibirsk State Agrarian University), 2: 37–47 (in Russian). https://doi.org/10.31677/2072-6724-2024-71-2-37-47.
Kolesnikov A.A. 2022. Analysis of Methods and Tools of Artificial Intelligence for Analysis and Interpretation of Active Remote Sensing Data. Bulletin of SSUGiT (Siberian State University of Geosystems and Technologies), 27(3): 74–94 (in Russian). https://doi.org/10.33764/2411-1759-2022-27-3-74-94.
Fomina E.S. 2023. Evaluation of the Efficiency of Using Specialized Neural Networks to Increase the Resolution of Images Obtained by Remote Sensing of the Earth. Control, Communications and Security Systems, 3: 71–90 (in Russian). https://doi.org/10.24412/2410-9916-2023-3-71-90.
Yakushev V.P., Zakharyan Yu.G., Blokhina S.Yu. 2022. Current Problems and Prospects for the Use of Remote Sensing of the Earth in Agriculture. Current Problems in Remote Sensing of the Earth from Space, 19(1): 287–294 (in Russian). https://doi.org/10.21046/2070-7401-2022-19-1-287-294.
Alom M.Z., Taha T.M., Yakopcic Ch., Westberg S., Sidike P., Nasrin M.S., Hasan M., Van Essen B.C., Awwal A.A.S., Asari V.K. 2019. A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics, 8(3): 292. https://doi.org/10.3390/electronics8030292.
Adugna T., Xu W., Fan J. 2022. Comparison of Random Forest and Support Vector Machine Classifiers for Regional Land Cover Mapping Using Coarse Resolution FY-3C Images. Remote Sensing, 14(3): 574. https://doi.org/10.3390/rs14030574.
Basheer S., Wang X., Farooque A.A., Nawaz R.A., Liu K., Adekanmbi T., Liu S. 2022. Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sensing, 14(19): 4978. https://doi.org/10.3390/rs14194978.
Breiman L. 2001. Random Forests. Machine Learning, 45: 5–32. https://doi.org/10.1023/A:1010933404324.
Carabantes M. 2020. Black-Box Artificial Intelligence: an Epistemological and Critical Analysis. AI & Society, 35: 309–317. https://doi.org/10.1007/s00146-019-00888-w.
Chen T., Guestrin C. 2016. Xgboost: A Scalable Tree Boosting System. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785–794. https://doi.org/10.1145/2939672.2939785.
Chen G., Weng Q., Hay G.J., He Y. 2018. Geographic Object-Based Image Analysis (GEOBIA): Emerging Trends and Future Opportunities. GIScience & Remote Sensing, 55(2): 159–182. https://doi.org/10.1080/15481603.2018.1426092.
Choi Y. 2023. GeoAI: Integration of Artificial Intelligence, Machine Learning, and Deep Learning with GIS. Applied Sciences, 13(6): 3895. https://doi.org/10.3390/app13063895.
Ekeanyanwu C.V., Obisakin I.F., Aduwenye P., Dede-Bamfo N. 2022. Merging GIS and Machine Learning Techniques: A Paper Review. Journal of Geoscience and Environment Protection, 10(9): 61–83. https://doi.org/10.4236/gep.2022.109004.
Ezzahouani B., Teodoro A., Kharki O.El., Jianhua L., Kotaridis I., Yuan X., Ma L. 2023. Remote Sensing Imagery Segmentation in Object-Based Analysis: A Review of Methods, Optimization, and Quality Evaluation Over the Past 20 years. Remote Sensing Applications: Society and Environment, 32: 101031. https://doi.org/10.1016/j.rsase.2023.101031.
Hossain M.D., Chen D. 2019. Segmentation for Object-Based Image Analysis (OBIA): A Review of Algorithms and Challenges from Remote Sensing Perspective. ISPRS Journal of Photogrammetry and Remote Sensing, 150: 115–134 р. https://doi.org/10.1016/j.isprsjprs.2019.02.009.
Janga B., Asamani G.P., Sun Z., Cristea N. 2023. A Review of Practical AI for Remote Sensing in Earth Sciences. Remote Sensing, 15(16): 4112. https://doi.org/10.3390/rs15164112.
Johnson B.A., Ma L. 2020. Image Segmentation and Object-Based Image Analysis for Environmental Monitoring: Recent Areas of Interest, Researchers’ Views on the Future Priorities. Remote Sensing, 12(11): 1772. https://doi.org/10.3390/rs12111772.
Li W., Hsu C.-Y. 2022. GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography. ISPRS International Journal of Geo-Information, 11(7): 385. https://doi.org/10.3390/ijgi11070385.
Mehmood M., Shahzad A., Zafar B., Shabbir A., Ali N. 2022. Remote Sensing Image Classi-Fication: A Comprehensive Review and Applications. Mathematical Problems in Engineering, 1: 5880959. https://doi.org/10.1155/2022/5880959.
Nalluri M., Pentela M., Eluri N.R. 2020. A Scalable Tree Boosting System: XG Boost. International Journal of Research Studies in Science, Engineering and Technology, 7(12): 36–51. https://doi.org/10.22259/2349-476X.0712005.
Radočaj D., Jurišić M. 2022. GIS-Based Cropland Suitability Prediction Using Machine Learning: A Novel Approach to Sustainable Agricultural Production. Agronomy, 12(9): 2210. https://doi.org/10.3390/agronomy12092210.
Sagan V., Coral R., Bhadra S., Alifu H., Al Akkad O., Giri A., Esposito F. 2024. Hyperfidelis: A Software Toolkit to Empower Precision Agriculture with GeoAI. Remote Sensing, 16(9): 1584. https://doi.org/10.3390/rs16091584.
Vali A., Comai S., Matteucci M. 2020. Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review. Remote Sensing, 12(15): 2495. https://doi.org/10.3390/rs12152495
Zhang Y., Liu J., Shen W. 2022. A Review of Ensemble Learning Algorithms Used in Remote Sensing Applications. Applied Sciences, 12(17): 8654. https://doi.org/10.3390/app12178654.
Zapf A., Castell S., Morawietz L., Karch A. 2016. Measuring Inter-Rater Reliability for Nominal Data – which Coefficients and Confidence Intervals are Appropriate? BMC Medical Research Methodology, 16: 1–10. https://doi.org/10.1186/s12874-016-0200-9.
Abstract views: 44
Share
Published
How to Cite
Issue
Section
Copyright (c) 2024 Regional Geosystems
This work is licensed under a Creative Commons Attribution 4.0 International License.
