Improved Mapping of Long-Term Forest Disturbance and Recovery Dynamics in the Subtropical China Using All Available Landsat Time-Series Imagery on Google Earth Engine Platform

Hua, Jianwen; Chen, Guangsheng; Yu, Lin; Ye, Qing; Jiao, Hongbo; Luo, Xifang

doi:10.1109/jstars.2021.3058421

Cited by 29 publications

(22 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They argued that this combined method is more accurate in detecting forest gain/loss due to large-scale disturbance events. Based on our previous study [46], we also found that this combination method can be effectively applied to detect the impacts of disturbance. In the future, we will apply this combined method to estimate forest damage in response to other devastating typhoon events in China.…”

Section: Uncertainties Implications and Outlooksmentioning

confidence: 85%

Impact Assessments of Typhoon Lekima on Forest Damages in Subtropical China Using Machine Learning Methods and Landsat 8 OLI Imagery

Chen

Cai

et al. 2021

Sustainability

Self Cite

View full text Add to dashboard Cite

Wind damage is one of the major factors affecting forest ecosystem sustainability, especially in the coastal region. Typhoon Lekima is among the top five most devastating typhoons in China and caused economic losses totaling over USD 8 billion in Zhejiang Province alone during 9–12 August 2019. However, there still is no assessment of its impacts on forests. Here we detected forest damage and its spatial distribution caused by Typhoon Lekima by classifying Landsat 8 OLI images using the random forest (RF) machine learning algorithm and the univariate image differencing (UID) method on the Google Earth Engine (GEE) platform. The accuracy assessment indicated a high overall accuracy (>87%) and kappa coefficient (>0.75) for forest-damage detection, as evaluated against field-investigated plot data, with better performance using the RF method. The total affected forest area by Lekima was 4598.87 km2, accounting for 8.44% of the total forest area in Zhejiang Province. The light-, moderate- and severe-damage forest areas were 2106.29 km2, 2024.26 km2 and 469.76 km2, respectively. Considering the damage severity, the net forest canopy loss fraction was 2.57%. The affected forest area and damage severity exhibited large spatial variations, which were affected by elevation, slope, precipitation and forest type. Our study indicated a larger uncertainty for affected forest area and a smaller uncertainty for the proportion of damage severity, based on multiple assessment approaches. This is among the first studies on forest damage due to typhoons at a regional scale in China, and the methods can be extended to examine the impacts of other super-strong typhoons on forests. Our study results on damage severity, spatial distribution and controlling factors could help local governments, the forest sector and forest landowners make decision on tree-planting planning and sustainable management after typhoon strikes and could also raise public and governmental awareness of typhoons’ damage on China’s inland forests.

show abstract

Section: Uncertainties Implications and Outlooksmentioning

confidence: 85%

Impact Assessments of Typhoon Lekima on Forest Damages in Subtropical China Using Machine Learning Methods and Landsat 8 OLI Imagery

Chen

Cai

et al. 2021

Sustainability

Self Cite

View full text Add to dashboard Cite

show abstract

“…Based on multiple data comparisons, several previous studies have also indicated that the GFC product significantly underestimated the forest loss and gain area at stand [44], national [19,45], and global scales [46]. In addition, this product only covered recent years and missed the 1980-2000 period when China has experienced stronger disturbance and initializations of several afforestation projects [16]. Therefore, it is necessary to localize and improve the forest change detection methods for China by considering the complicated forest and topographic conditions and training and evaluating the algorithms using more intensive local observational data, and generate provincial and national forest loss and gain dataset using the validated methods.…”

Section: Introductionmentioning

confidence: 99%

“…Diseases outbreaks have affected 22,954 km 2 of forest area in 2019, and insects and pests have affected 81,146 km 2 of forest area according to the NFI report. In addition to forestry policies and disturbances, other factors such as elevation, local economic development condition, and local forestry policies were reported to affect forest gain and loss [16][17][18]. All above factors could greatly affect the spatial and temporal patterns in forest gain and loss at different scales; however, few regional studies have assessed their impacts in China [19].…”

Section: Introductionmentioning

confidence: 99%

“…For example, [36] proposed an ensemble approach for predicting disturbance and subsequent recovery levels for each disturbed pixel, and argued that this approach could simultaneously describe the levels of both disturbance and subsequent recovery as a single hybrid pattern; [37] developed the integrated approach between the LandTrendr and gradient nearest neighbor (GNN) imputation method to detect large tree and snag distributions; [38] detected forest harvest and post-harvest recovery in Japan using the integrated RF and LandTrendr approach, and concluded that this approach can provide valuable information on a country-wide replantation activity in harvest areas. However, due to the more complex terrain, forest types, and climate conditions in China, our previous study [16] indicated that some other factors such as elevation and image textures could also be important factors for detecting forest loss and gain in China.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Contrasting Forest Loss and Gain Patterns in Subtropical China Detected Using an Integrated LandTrendr and Machine-Learning Method

et al. 2022

View full text Add to dashboard Cite

China has implemented a series of forestry law, policies, regulations, and afforestation projects since the 1970s. However, their impacts on the spatial and temporal patterns of forests have not been fully assessed yet. The lack of an accurate, high-resolution, and long-term forest disturbance and recovery dataset has impeded this assessment. Here we improved the forest loss and gain detections by integrating the LandTrendr change detection algorithm with the Random Forest (RF) machine-learning method and applied it to assess forest loss and gain patterns in the Zhejiang, Jiangxi, and Guangxi Provinces of the subtropical vegetation in China. The accuracy evaluation indicated that our approach can adequately detect the spatial and temporal distribution patterns in forest gain and loss, with an overall accuracy of 93% and the Kappa coefficient of 0.89. The forest loss area was 8.30 × 104 km2 in the Zhejiang, Jiangxi, and Guangxi Provinces during 1986–2019, accounting for 43.52% of total forest area in 1986, while the forest gain area was 20.25 × 104 km2, accounting for 106.19% of total forest area in 1986. Although the interannual variation patterns were similar among three provinces, the forest loss and gain area and the magnitude of change trends were significantly different. Guangxi has the largest forest loss and gain area and increasing trends, followed by Jiangxi, and the least in Zhejiang. The variations in annual forest loss and gain area can be mostly explained by the timelines of major forestry policies and regulations. Our study would provide an applicable method and data for assessing the impacts of forest disturbance events and forestry policies and regulations on the spatial and temporal patterns of forest loss and gain in China, and further contributing to regional and national forest carbon and greenhouse gases budget estimations.

show abstract

“…The spatial and spectral resolutions offered by Landsat and MODIS are well-suited for deforestation analysis; hence, there are various studies dealing with deforestation that analyze datasets coming from Landsat and MODIS satellites ( [7], [14], [19]). With remote sensing, deforestation monitoring systems use a number of automatic methods based on change detection techniques [13], e.g., image processing and analysis methods [16], [30] or ML techniques [12], [35].…”

mentioning

confidence: 99%

A Vision Transformer Model for Convolution-Free Multilabel Classification of Satellite Imagery in Deforestation Monitoring

Kaselimi

Voulodimos

Daskalopoulos

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Understanding the dynamics of deforestation and land uses of neighboring areas is of vital importance for the design and development of appropriate forest conservation and management policies. In this article, we approach deforestation as a multilabel classification (MLC) problem in an endeavor to capture the various relevant land uses from satellite images. To this end, we propose a multilabel vision transformer model, ForestViT, which leverages the benefits of the self-attention mechanism, obviating any convolution operations involved in commonly used deep learning models utilized for deforestation detection. Experimental evaluation in open satellite imagery datasets yields promising results in the case of MLC, particularly for imbalanced classes, and indicates ForestViT's superiority compared with well-established convolutional structures (ResNET, VGG, DenseNet, and ModileNet neural networks). This superiority is more evident for minority classes.

show abstract

Improved Mapping of Long-Term Forest Disturbance and Recovery Dynamics in the Subtropical China Using All Available Landsat Time-Series Imagery on Google Earth Engine Platform

Cited by 29 publications

References 61 publications

Impact Assessments of Typhoon Lekima on Forest Damages in Subtropical China Using Machine Learning Methods and Landsat 8 OLI Imagery

Impact Assessments of Typhoon Lekima on Forest Damages in Subtropical China Using Machine Learning Methods and Landsat 8 OLI Imagery

Contrasting Forest Loss and Gain Patterns in Subtropical China Detected Using an Integrated LandTrendr and Machine-Learning Method

A Vision Transformer Model for Convolution-Free Multilabel Classification of Satellite Imagery in Deforestation Monitoring

Contact Info

Product

Resources

About