Per-pixel land cover accuracy prediction: A random forest-based method with limited reference sample data

Ebrahimy, Hamid; Mirbagheri, Babak; Matkan, A A; Azadbakht, Mohsen

doi:10.1016/j.isprsjprs.2020.11.024

Cited by 39 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An RF classifier is generally composed of a large number of base weak classifiers, each of which is an independent individual classification and regression tree (CART). The RF-based model has been widely employed in RS communities and applied in various LULC classification tasks [22,[45][46][47]. To implement the RF, two fundamental parameters are needed in an RF: one is the number of trees (ntree) for constructing a whole forest, and the other is the number of picked features (mty) that are used for node splitting.…”

Section: Methodsmentioning

confidence: 99%

Characterizing the Up-To-Date Land-Use and Land-Cover Change in Xiong’an New Area from 2017 to 2020 Using the Multi-Temporal Sentinel-2 Images on Google Earth Engine

Luo

Chu

et al. 2021

IJGI

View full text Add to dashboard Cite

Land use and land cover (LULC) are fundamental units of human activities. Therefore, it is of significance to accurately and in a timely manner obtain the LULC maps where dramatic LULC changes are undergoing. Since 2017 April, a new state-level area, Xiong’an New Area, was established in China. In order to better characterize the LULC changes in Xiong’an New Area, this study makes full use of the multi-temporal 10-m Sentinel-2 images, the cloud-computing Google Earth Engine (GEE) platform, and the powerful classification capability of random forest (RF) models to generate the continuous LULC maps from 2017 to 2020. To do so, a novel multiple RF-based classification framework is adopted by outputting the classification probability based on each monthly composite and aggregating the multiple probability maps to generate the final classification map. Based on the obtained LULC maps, this study analyzes the spatio-temporal changes of LULC types in the last four years and the different change patterns in three counties. Experimental results indicate that the derived LULC maps achieve high accuracy for each year, with the overall accuracy and Kappa values no less than 0.95. It is also found that the changed areas account for nearly 36%, and the dry farmland, impervious surface, and other land-cover types have changed dramatically and present varying change patterns in three counties, which might be caused by the latest planning of Xiong’an New Area. The obtained 10-m four-year LULC maps in this study are supposed to provide some valuable information on the monitoring and understanding of what kinds of LULC changes have taken place in Xiong’an New Area.

show abstract

Section: Methodsmentioning

confidence: 99%

Characterizing the Up-To-Date Land-Use and Land-Cover Change in Xiong’an New Area from 2017 to 2020 Using the Multi-Temporal Sentinel-2 Images on Google Earth Engine

Luo

Chu

et al. 2021

IJGI

View full text Add to dashboard Cite

show abstract

“…Procedures for the classification of remote sensing images using shallow classifiers, such as RF and SVM include feature extraction and classification. Spatial, temporal, and spectral data of satellite images are transformed into the feature vectors in the feature extraction process, while these extracted features are classified into different land cover types in the classification stage [31], [32], [33]. It is worth highlighting that the manual feature engineering of the conventional classification methods (i.e., the selection of the most appropriate extracted features in the classification of satellite data) significantly affects the final classification results.…”

Section: A Image Classificationmentioning

confidence: 99%

3-D Hybrid CNN Combined With 3-D Generative Adversarial Network for Wetland Classification With Limited Training Data

Jamali¹,

Mahdianpari

Mohammadimanesh³

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recently, deep learning algorithms, specifically convolutional neural networks (CNNs), have played an important role in remote sensing image classification, including wetland mapping. However, one limitation of deep CNN for classification is its requirement for a great number of training samples. This limitation is particularly enhanced when the classes of interest are spectrally similar, such as that of wetland types, and the training samples are limited. This article presents a novel approach named 3-D hybrid generative adversarial network (3-D hybrid GAN) that addresses the limited training sample issue in the classification of remote sensing imagery with a focus on complex wetland classification. We used a conditional map unit that generates synthetic training samples for only classes with a lower number of training samples to improve the per-class accuracy of wetlands. This procedure overcomes the issue of imbalanced data in conventional wetland mapping. Based on the achieved results, better classification accuracy is obtained by integrating a 3-D generative adversarial network (3-D GAN) and the CNN network of a 3-D hybrid CNN using both 3-D and 2-D convolutional filters. Experimental results on the avalon pilot site located in eastern Newfoundland, Canada, and covering five wetland types of bog, fen, marsh, swamp, and shallow water demonstrate that our model significantly outperforms other CNN models, including the HybridSN, SpectralNet, MLP-mixer, as well as a conventional algorithm of random forest for complex wetland classification by approximately 1% to 51% in terms of F-1 score.

show abstract

“…For example, the maximum likelihood algorithm [19] is often unable to identify multi-dimensional remote sensing data correctly. For the classification of high-dimensional data, algorithms such as DT [29][30][31], RF [29,30,32], and SVM [33][34][35] performed better. Considering the success of these classification models for remote sensing image classification, deep learning approaches for remote sensing image classification have attracted great attention [36][37][38][39].…”

Section: Related Workmentioning

confidence: 99%

Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery

Jamali

Mahdianpari

2022

Water

View full text Add to dashboard Cite

The emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, particularly in the classification of wetlands. State-of-the-art Natural Language Processing (NLP) algorithms, on the other hand, are transformers. Despite the fact that transformers have been utilized for a few remote sensing applications, they have not been compared to other well-known CNN networks in complex wetland classification. As such, for the classification of complex coastal wetlands in the study area of Saint John city, located in New Brunswick, Canada, we modified and employed the Swin Transformer algorithm. Moreover, the developed transformer classifier results were compared with two well-known deep CNNs of AlexNet and VGG-16. In terms of average accuracy, the proposed Swin Transformer algorithm outperformed the AlexNet and VGG-16 techniques by 14.3% and 44.28%, respectively. The proposed Swin Transformer classifier obtained F-1 scores of 0.65, 0.71, 0.73, 0.78, 0.82, 0.84, and 0.84 for the recognition of coastal marsh, shrub, bog, fen, aquatic bed, forested wetland, and freshwater marsh, respectively. The results achieved in this study suggest the high capability of transformers over very deep CNN networks for the classification of complex landscapes in remote sensing.

show abstract

Per-pixel land cover accuracy prediction: A random forest-based method with limited reference sample data

Cited by 39 publications

References 43 publications

Characterizing the Up-To-Date Land-Use and Land-Cover Change in Xiong’an New Area from 2017 to 2020 Using the Multi-Temporal Sentinel-2 Images on Google Earth Engine

Characterizing the Up-To-Date Land-Use and Land-Cover Change in Xiong’an New Area from 2017 to 2020 Using the Multi-Temporal Sentinel-2 Images on Google Earth Engine

3-D Hybrid CNN Combined With 3-D Generative Adversarial Network for Wetland Classification With Limited Training Data

Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery

Contact Info

Product

Resources

About