Forest Type Classification Based on Integrated Spectral-Spatial-Temporal Features and Random Forest Algorithm—A Case Study in the Qinling Mountains

Cheng, Kai; Wang, Juanle

doi:10.3390/f10070559

Cited by 42 publications

(32 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The methodological workflow ( Figure 2) consisted of the following steps: (1) preprocessing, which involved the identification and masking of clouds, cirrus, and aerosols [25], image composition, and Normalized Difference Vegetation Index (NDVI) time-series creation; (2) classification in which TWDTW, RF, and SVM were used to map the target classes; and (3) comparison and evaluation in which the forest-type maps obtained by TWDTW, RF, and SVM were compared in terms of spatial identification and quantity, and the classification accuracy of each method was assessed.…”

Section: Methodsmentioning

confidence: 99%

“…The potential of time-series data has been evaluated for forest-type classifications in various studies [22][23][24][25]. However, the application of Sentinel-2 and Landsat-8 time-series images for forest-type classification in a mountainous area had not been reported.…”

Section: Combination Of Sentinel-2 and Landsat-8 Time Seriesmentioning

confidence: 99%

“…Zhu and Liu [24] mapped detailed forest types using dense Landsat time series and revealed that using Landsat time series can significantly improve the accuracy of forest-type mapping compared with a single image. Cheng et al [25] took Qinling Mountains in China as an example, and proved the potential application of Sentinel-2 time series data for forest-type classification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Cheng

Wang

2019

Forests

Self Cite

View full text Add to dashboard Cite

Efficient methodologies for mapping forest types in complicated mountain areas are essential for the implementation of sustainable forest management practices and monitoring. Existing solutions dedicated to forest-type mapping are primarily focused on supervised machine learning algorithms (MLAs) using remote sensing time-series images. However, MLAs are challenged by complex and problematic forest type compositions, lack of training data, loss of temporal data caused by clouds obscuration, and selection of input feature sets for mountainous areas. The time-weighted dynamic time warping (TWDTW) is a supervised classifier, an adaptation of the dynamic time warping method for time series analysis for land cover classification. This study evaluates the performance of the TWDTW method that uses a combination of Sentinel-2 and Landsat-8 time-series images when applied to complicated mountain forest-type classifications in southern China with complex topographic conditions and forest-type compositions. The classification outputs were compared to those produced by MLAs, including random forest (RF) and support vector machine (SVM). The results presented that the three forest-type maps obtained by TWDTW, RF, and SVM have high consistency in spatial distribution. TWDTW outperformed SVM and RF with mean overall accuracy and mean kappa coefficient of 93.81% and 0.93, respectively, followed by RF and SVM. Compared with MLAs, TWDTW method achieved the higher classification accuracy than RF and SVM, with even less training data. This proved the robustness and less sensitivities to training samples of the TWDTW method when applied to mountain forest-type classifications.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Combination Of Sentinel-2 and Landsat-8 Time Seriesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Cheng

Wang

2019

Forests

Self Cite

View full text Add to dashboard Cite

show abstract

“…The SNT zone spans the warm temperate and subtropical zones, and is the most important geological-ecological transition zone on the Chinese mainland, with a high degree of environmental complexity, biodiversity, and climate sensitivity [18]. It has mostly evergreen broad-leaved, deciduous broad-leaved, and deciduous needle-leaved forests [18,19].…”

Section: Study Areamentioning

confidence: 99%

Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features

2021

Self Cite

View full text Add to dashboard Cite

The comprehensive application of spectral, spatial, and temporal (SST) features derived from remote sensing images is a significant technique for classifying and mapping forest types. Facing limitations in the availability of detailed forest type identification processes for large regions, a forest type classification framework based on SST features was developed in this study. The advantages of Sentinel-2 and Landsat series imagery were used to extract SST forest type classification features, using red-edge bands, a gray-level co-occurrence matrix, and harmonic analysis, with the assistance of the Google Earth Engine platform. Considering four representative Chinese geographic regions—middle and high latitudes, complex mountainous areas, cloudy and rainy areas, and the N–S climate transition zone—our method was proven to be effective, with overall classification accuracies > 85%. The scheme to assess the importance of SST features for forest classification in various regions was designed using the Gini criterion in the random forest algorithm and revealed that spectral features were more effective in classifying forest types with complex compositions. Temporal features were found to be favorable for identifying forest types with obvious evergreen and deciduous growth patterns, while spatial features produced better classification results for forest types with different spatial structures, such as needle- or broad-leaved forests. The findings of this study can provide a reference for feature selection in remote sensing forest type classification processes, and identifying forest types in this way could provide support for the accurate and sustainable management of forest resources.

show abstract

“…Land cover changes information is useful to achieve a better perspective of landscape dynamics and is also proper for evaluating the sustainability of natural resources [3,4]. Thus, ground cover monitoring and mapping are required to investigate spatial planning and environmental examination [5,6]. Additionally, land Thus, we calculated the rate of land cover change throughout the study.…”

Section: Introductionmentioning

confidence: 99%

Land Cover Changes from 1990 to 2019 in Papua, Indonesia: Results of the Remote Sensing Imagery

Letsoin

Herák

Rahmawan³

et al. 2020

Sustainability

View full text Add to dashboard Cite

Long-term land cover changes play a significant driver of ecosystem and function of natural biodiversity. Hence, their analysis can be used for evaluating and supporting government plans, especially conservation and management of natural habitats such as sago palm. In Papua Province of Indonesia, sago palm has been stated as one of the priority plants in the Medium-Term Development Plan (R.P.J.M.). However, limited studies have examined this palm in one of the Regencies of Papua Province, namely, Merauke Regency. In this study, we performed remotely sensed data imagery and supervised classification to produce land cover maps from 1990 to 2019. During the study period, twenty-one land cover classes were identified. The six classes of the natural forest consist of primary dryland forest, secondary dryland forest, primary mangrove forest, secondary mangrove forest, primary swamp forest, and secondary swamp forest; thus, fifteen classes of non-forested area. Concerning the sago palm habitat, our study evaluated two different categories (1) based on the land cover scheme from the Ministry of Environment and Forestry and (2) according to the peatland land cover ecosystem in Papua. Based on paired samples t-test, the result indicated statistically significant changes specifically at primary dryland (p-value = 0.015), grassland (p-value = 0.002) and swamp (p-value = 0.007). Twelve from 20 districts of Merauke Regency tend to lose the forecasted natural habitat of the sago palm. Therefore, this study suggests the further need to recognize and estimate the yield of sago palm area in these various ecosystems.

show abstract

Forest Type Classification Based on Integrated Spectral-Spatial-Temporal Features and Random Forest Algorithm—A Case Study in the Qinling Mountains

Cited by 42 publications

References 32 publications

Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features

Land Cover Changes from 1990 to 2019 in Papua, Indonesia: Results of the Remote Sensing Imagery

Contact Info

Product

Resources

About