Machine learning in modelling land-use and land cover-change (LULCC): Current status, challenges and prospects

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 822, P. 153559 - 153559

Published: Jan. 31, 2022

Language: Английский

---

Land use/land cover change and its impact on surface urban heat island and urban thermal comfort in a metropolitan city

Urban Climate, Journal Year: 2021, Volume and Issue: 41, P. 101052 - 101052

Published: Dec. 16, 2021

Language: Английский

---

Identifying core driving factors of urban land use change from global land cover products and POI data using the random forest method

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2021, Volume and Issue: 103, P. 102475 - 102475

Published: Aug. 8, 2021

Rapid urbanization at the expense of environment led to a reduction in vegetation cover, and consequently aggravated land degradation, urban water logging, heat island effect other effects. Revealing driving mechanism behind use change facilitates deeper insight into human biophysical effects process thereby supports sustainable development. This work proposed margin-based measure random forest for core factor identification change, which mainly included constructed land, bodies, etc., using multitemporal global cover products point-of-interest (POI) data. Taking Wuhan from 2010 2020 as case study, method was employed sort forces 24 factors. The results suggested that more reliable sensitive than traditional importance when detecting change. Meanwhile, both values ranking orders factors measured by were stable regardless similarity chosen applied. findings also showed topographic conditions persistently affected while transportation factors, instead business services, gradually became most important last 10 years.

Language: Английский

---

Machine Learning Applications based on SVM Classification A Review

Qubahan Academic Journal, Journal Year: 2021, Volume and Issue: 1(2), P. 81 - 90

Published: April 28, 2021

Extending technologies and data development culminated in the need for quicker more reliable processing of massive sets. Machine Learning techniques are used excessively. This paper, therefore, attempts to deal with processing, using a support vector machine (SVM) algorithm different fields since it is reliable, efficient classification method area learning. Accordingly, many works have been explored this paper cover use SVM classifier. Classification based on has like face recognition, diseases diagnostics, text sentiment analysis, plant disease identification intrusion detection system network security application. Based study, can be concluded that classifier obtained high accuracy results most applications, specifically, recognition applications.

Language: Английский

---

Using artificial intelligence and data fusion for environmental monitoring: A review and future perspectives

Information Fusion, Journal Year: 2022, Volume and Issue: 86-87, P. 44 - 75

Published: June 25, 2022

Language: Английский

---

Development of classification system for LULC using remote sensing and GIS

Global Transitions Proceedings, Journal Year: 2021, Volume and Issue: 2(1), P. 8 - 17

Published: Jan. 29, 2021

This article demonstrations the techniques for land classification and development stages that began in 1950 till now. It highlights findings of research efforts from 220 studies worked this domain. The was manual processes evolved into numerical digital with emergence technology revolution Artificial Intelligence algorithms. included an inventory all methods traditional recent used classification. Most use cover classifiers have been comparing to determine best characteristics each points will help develop accuracy. be significant upcoming researchers understand various techniques. efficient classifier motivates new classifiers.

Language: Английский

---

U-Net-LSTM: Time Series-Enhanced Lake Boundary Prediction Model

Land, Journal Year: 2023, Volume and Issue: 12(10), P. 1859 - 1859

Published: Sept. 29, 2023

Change detection of natural lake boundaries is one the important tasks in remote sensing image interpretation. In an ordinary fully connected network, or CNN, signal neurons each layer can only be propagated to upper layer, and processing samples independent at moment. However, for time-series data with transferability, learned change information needs recorded utilized. To solve above problems, we propose a boundary prediction model combining U-Net LSTM. The ensemble LSTMs helps improve overall accuracy robustness by capturing spatial temporal nuances data, resulting more precise predictions. This study selected Lake Urmia as research area used annual panoramic images from 1996 2014 (Lat: 37°00′ N 38°15′ N, Lon: 46°10′ E 44°50′ E) obtained Google Earth Professional Edition 7.3 software set. uses network extract multi-level features analyze trend boundaries. LSTM module introduced after optimize predictive using historical storage forgetting well current input data. method enables automatically fit time series mine deep changes. Through experimental verification, model’s changes training reach 89.43%. Comparative experiments existing U-Net-STN show that U-Net-LSTM this has higher lower mean square error.

Language: Английский

---

Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(19), P. 4978 - 4978

Published: Oct. 6, 2022

Accurate land use cover (LULC) classification is vital for the sustainable management of natural resources and to learn how landscape changing due climate. For accurate efficient LULC classification, high-quality datasets robust methods are required. With increasing availability satellite data, geospatial analysis tools, methods, it essential systematically assess performance different combinations data help select best approach classification. Therefore, this study aims evaluate two commonly used platforms (i.e., ArcGIS Pro Google Earth Engine) with Landsat, Sentinel, Planet) through a case city Charlottetown in Canada. Specifically, three classifiers Pro, including support vector machine (SVM), maximum likelihood (ML), random forest/random tree (RF/RT), utilized develop maps over period 2017–2021. Whereas four Engine, SVM, RF/RT, minimum distance (MD), regression (CART), same period. To identify most classifier, overall accuracy kappa coefficient each classifier calculated throughout all platforms, methods. Change detection then conducted using quantify changes Results show that SVM both Engine presents compared other classifiers. In particular, shows an 89% 91% 94% Planet. Similarly, 87% Landsat 8 92% Sentinel 2. Furthermore, change results 13.80% 14.10% forest areas have been turned into bare urban class, respectively, 3.90% has converted area from 2017 2021, suggesting intensive urbanization. The will provide scientific basis selecting remote sensing imagery maps.

Language: Английский

---

Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(7), P. 1349 - 1349

Published: April 1, 2021

With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating managing changes in as created by ecosystem use. The main objective our study is evaluate performance Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), Mahalanobis (MH) compare them order generate a LULC map using data from Sentinel 2 Landsat 8 satellites. Further, we also investigate effect penalty parameter on SVM results. Our uses different kernel functions hidden layers ANN algorithms, respectively. We generated training validation datasets Google Earth images GPS prior pre-processing data. In next phase, classified algorithms. Ultimately, outcomes, used confusion matrix images. results showed that with optimal tuning parameters, classifier yielded highest overall accuracy (OA) 94%, performing better both compared other methods. addition, scenes, date was slightly more 8. parametric MD MLC provided lowest 80.85% 74.68% contrast, evaluation parameters linear 150 200 accuracies. classification increasing drastically reduces datasets, reducing zero three layers.

Language: Английский

---

Predicting the impacts of land use/land cover changes on seasonal urban thermal characteristics using machine learning algorithms

Building and Environment, Journal Year: 2022, Volume and Issue: 217, P. 109066 - 109066

Published: April 7, 2022

Language: Английский

---