Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic
The preparation of geological maps based on field data and the application of aerial photographs have always been an error because of the structural diversity of the earth and the difficulty of accessing certain regions. But in recent decades, the use of satellite imagery has but in recent decades,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Iranian Scientific Association of Desert Management and Control (ISADMC)
2022-11-01
|
| Series: | مدیریت بیابان |
| Subjects: | |
| Online Access: | http://www.jdmal.ir/article_248114_b18843d460a63936375fda35f81a2896.pdf |
| _version_ | 1811161535939084288 |
|---|---|
| author | Fatemeh Kamali Mohammad Mansourmoghaddam Hamidreza Ghafarian malmiri Fahime Arabi aliabad |
| author_facet | Fatemeh Kamali Mohammad Mansourmoghaddam Hamidreza Ghafarian malmiri Fahime Arabi aliabad |
| author_sort | Fatemeh Kamali |
| collection | DOAJ |
| description | The preparation of geological maps based on field data and the application of aerial photographs have always been an error because of the structural diversity of the earth and the difficulty of accessing certain regions. But in recent decades, the use of satellite imagery has but in recent decades, the use of satellite imagery has gone a long way to increasing the accuracy and timeliness of geological mapping. The purpose of the current study is to investigate the applicability of Landsat 8 satellite images and object-oriented pixel classification methods in mapping the geological formations of some part of the Shirkuh Mountain range in Yazd province. This area is part of the scattered mountain range of Central Iran with a dry climate and minimal vegetation. Initially, enhanced operations were performed to identify geological information’s using MNF, PCA and FCC processing. Then, the images were classified using object-oriented algorithms (BAYES, SVM, KNN, Decision Tree and Random Forest), neural network (ARTMAP, RBF, MLP and SOM), and base pixels (Maximum Likelihood, Minimum Distance, Mahalanobis and SAM). Next, the error rate of each method was calculated using Boolean logic and kappa coefficient. The results showed that the maximum probability classification with kappa coefficient of 75% in the base pixel category, Fuzzy ARTMAP classification in neural network method with kappa coefficient of 72% and Bayesian classification in object-oriented method with kappa coefficient of 82% have the best results among other methods. These results show that the methods mentioned in the identification and separation of geological formations are effective. The SAM of pixel-based methods, SOM of neural network methods and RF of object-oriented methods with 49%, 64% and 61%, respectively, showed the lowest accuracy in each category. |
| first_indexed | 2024-04-10T06:15:55Z |
| format | Article |
| id | doaj.art-3052c5b4017f4cc5b7475a03c97442a8 |
| institution | Directory Open Access Journal |
| issn | 2476-3985 2476-3721 |
| language | fas |
| last_indexed | 2024-04-10T06:15:55Z |
| publishDate | 2022-11-01 |
| publisher | Iranian Scientific Association of Desert Management and Control (ISADMC) |
| record_format | Article |
| series | مدیریت بیابان |
| spelling | doaj.art-3052c5b4017f4cc5b7475a03c97442a82023-03-02T06:53:46ZfasIranian Scientific Association of Desert Management and Control (ISADMC)مدیریت بیابان2476-39852476-37212022-11-01103173610.22034/jdmal.2021.534277.1340248114Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean LogicFatemeh Kamali0Mohammad Mansourmoghaddam1Hamidreza Ghafarian malmiri2Fahime Arabi aliabad3Master of Remote Sensing and GIS, Department of Geography, Campus of Humanities and Social Sciences, Yazd University, Yazd, Iran.PhD Student in Remote Sensing, Center for Remote Sensing and GIS Research, Shahid Beheshti University, Tehran, Iran.Assistant Professor, Department of Geography, Department of Environmental Planning, Campus of Humanities and Social Sciences, Yazd University, Yazd, Iran.MSc of Arid Lands Management, Faculty of Natural Resources and Eremology, Yazd University, Iran.The preparation of geological maps based on field data and the application of aerial photographs have always been an error because of the structural diversity of the earth and the difficulty of accessing certain regions. But in recent decades, the use of satellite imagery has but in recent decades, the use of satellite imagery has gone a long way to increasing the accuracy and timeliness of geological mapping. The purpose of the current study is to investigate the applicability of Landsat 8 satellite images and object-oriented pixel classification methods in mapping the geological formations of some part of the Shirkuh Mountain range in Yazd province. This area is part of the scattered mountain range of Central Iran with a dry climate and minimal vegetation. Initially, enhanced operations were performed to identify geological information’s using MNF, PCA and FCC processing. Then, the images were classified using object-oriented algorithms (BAYES, SVM, KNN, Decision Tree and Random Forest), neural network (ARTMAP, RBF, MLP and SOM), and base pixels (Maximum Likelihood, Minimum Distance, Mahalanobis and SAM). Next, the error rate of each method was calculated using Boolean logic and kappa coefficient. The results showed that the maximum probability classification with kappa coefficient of 75% in the base pixel category, Fuzzy ARTMAP classification in neural network method with kappa coefficient of 72% and Bayesian classification in object-oriented method with kappa coefficient of 82% have the best results among other methods. These results show that the methods mentioned in the identification and separation of geological formations are effective. The SAM of pixel-based methods, SOM of neural network methods and RF of object-oriented methods with 49%, 64% and 61%, respectively, showed the lowest accuracy in each category.http://www.jdmal.ir/article_248114_b18843d460a63936375fda35f81a2896.pdflithologyremote sensingarid regionsneural networkyazd |
| spellingShingle | Fatemeh Kamali Mohammad Mansourmoghaddam Hamidreza Ghafarian malmiri Fahime Arabi aliabad Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic مدیریت بیابان lithology remote sensing arid regions neural network yazd |
| title | Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic |
| title_full | Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic |
| title_fullStr | Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic |
| title_full_unstemmed | Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic |
| title_short | Evaluation of Object-Oriented, Pixel-Based Classification, and Neural Network in The Separation of Geological Formations Using Landsat 8 Images and Boolean Logic |
| title_sort | evaluation of object oriented pixel based classification and neural network in the separation of geological formations using landsat 8 images and boolean logic |
| topic | lithology remote sensing arid regions neural network yazd |
| url | http://www.jdmal.ir/article_248114_b18843d460a63936375fda35f81a2896.pdf |
| work_keys_str_mv | AT fatemehkamali evaluationofobjectorientedpixelbasedclassificationandneuralnetworkintheseparationofgeologicalformationsusinglandsat8imagesandbooleanlogic AT mohammadmansourmoghaddam evaluationofobjectorientedpixelbasedclassificationandneuralnetworkintheseparationofgeologicalformationsusinglandsat8imagesandbooleanlogic AT hamidrezaghafarianmalmiri evaluationofobjectorientedpixelbasedclassificationandneuralnetworkintheseparationofgeologicalformationsusinglandsat8imagesandbooleanlogic AT fahimearabialiabad evaluationofobjectorientedpixelbasedclassificationandneuralnetworkintheseparationofgeologicalformationsusinglandsat8imagesandbooleanlogic |