Bamboo Forest Mapping in China Using the Dense Landsat 8 Image Archive and Google Earth Engine

Qi, Shanshan; Song, Bin; Liu, Chong; Gong, Peng; Luo, Jin; Zhang, Meinan; Xiong, Tianwei

doi:10.3390/rs14030762

Cited by 32 publications

(19 citation statements)

References 62 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, combining multiple feature variables helped to improve the classification accuracy, which can also be proved from previous studies. For example, Qi et al [ 54 ] found that NDVI, NDMI, and texture features make bamboo forest classification more accurate and reliable. Li et al [ 53 ] combined spectral bands, vegetation indices, texture, and topographic features to map the distribution of bamboo forests in Zhejiang from 1990 to 2014, and the OA was above 85%.…”

Section: Resultsmentioning

confidence: 99%

“…Compared with similar studies, the UA of Phyllostachys edulis was 4.5–14.5% higher than that of SVM [ 67 , 69 ]. The highest UA of bamboo forest is about 7.0% and 15.5% higher than that of decision tree and random forest, respectively [ 54 , 99 ]. The OA of bamboo forest is comparable to that of the artificial neural network, but the UA is higher than that of the artificial neural network [ 104 ].…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies have shown that spectral features, vegetation indices, texture features, and topographic features, which are commonly used in image classification, can improve classification to varying degrees [ 53 , 54 , 55 ]. The spectral features are decisive features that discriminate between species.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Zhou

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

Mapping the distribution of bamboo species is vital for the sustainable management of bamboo and for assessing its ecological and socioeconomic value. However, the spectral similarity between bamboo species makes this work extremely challenging through remote sensing technology. Existing related studies rarely integrate multiple feature variables and consider how to quantify the main factors affecting classification. Therefore, feature variables, such as spectra, topography, texture, and vegetation indices, were used to construct the XGBoost model to identify bamboo species using the Zhuhai-1 Orbita hyperspectral (OHS) imagery in the Southern Sichuan Bamboo Sea and its surrounding areas in Sichuan Province, China. The random forest and Spearman’s rank correlation analysis were used to sort the main variables that affect classification accuracy and minimize the effects of multicollinearity among variables. The main findings were: (1) The XGBoost model achieved accurate and reliable classification results. The XGBoost model had a higher overall accuracy (80.6%), kappa coefficient (0.708), and mean F1-score (0.805) than the spectral angle mapper (SAM) method; (2) The optimal feature variables that were important and uncorrelated for classification accuracy included the blue band (B1, 464–468 nm), near-infrared band (B27, 861–871 nm), green band (B5, 534–539 nm), elevation, texture feature mean, green band (B4, 517–523 nm), and red edge band (B17, 711–720 nm); and (3) the XGBoost model based on the optimal feature variable selection showed good adaptability to land classification and had better classification performance. Moreover, the mean F1-score indicated that the model could well balance the user’s and producer’s accuracy. Additionally, our study demonstrated that OHS imagery has great potential for land cover classification and that combining multiple features to enhance classification is an approach worth exploring. Our study provides a methodological reference for the application of OHS images for plant species identification.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Zhou

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…MODIS images were used to constitute a MODIS dataset with four time (2005, 2010, 2015, 2020), spatial resolution of 500 m, and three products (MOD091, MOD11A2, MOD13A1) in the GEE platform [27], and the GEE platform was used to calculate the RSEIs of the study area for 2005, 2010, 2015, and 2020 RSEI.…”

Section: Methodsmentioning

confidence: 99%

Analysis of the Coupled Assessment of Ecosystem Health and Its Spatial and Temporal Evolution in Fujian China

Cao¹,

Tang²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

As the first pilot ecological civilization zone in China, Fujian Province has an excellent ecological environment quality, and its ecological environment-related indices continue to be among the highest in the country. In order to investigate the causes of the excellent ecological quality in Fujian Province in the past 15 years, this paper selects MODIS images, land use data and provincial and municipal statistical yearbook data of Fujian province from 2005 to 2020 as data sources, evaluates the ecological system health of Fujian Province by remote-sensing ecological index (i.e. RSEI), constructs the land use intensity system of Fujian Province at the same time, and uses a coupled coordination model to analyze the coupling between RSEI and The coupled coordination model was used to analyze the coupling relationship between RSEI and land use intensity, and finally the spatial and temporal evolution of ecological health in Fujian Province from 2005 to 2020 was analyzed. The results show that the coupled coordination between land use intensity and ecosystem health in Fujian province showed a continuous increase between 2005 and 2020, especially in Ningde, where the increase was most significant, from 0.0993 to 0.963, this pattern of spatial distribution is lower in the south-eastern coastal region than in the north-western interior, higher in the south-western region than in the north-western region, and higher in the north-eastern region than in the south-eastern region. In terms of the type of role, the land use intensity of most cities in Fujian Province in 2005 played an obvious role in blocking the degree of ecosystem health, but as time changed, urban land use continued to be optimized and reached moderate or even high quality coordination with the quality of the ecological environment, but Xiamen City developed relatively slowly and its 2020 coupling degree value was 0.315, which was still in mild disorder. This study fills a gap in the research mechanism of the interaction between the degree of ecosystem health and land use intensity, and also provides a new perspective for the construction of ecological civilization and the assessment of the degree of ecosystem health in Fujian Province and the whole country.

show abstract

“…Nowadays, Landsat 8 satellite image data can completely overcome the limitations of traditional methods in monitoring and evaluating drought [12]. It can provide a synoptic and comprehensive view of the area, allowing for the detection of changes in vegetation health, land surface temperature, and precipitation patterns [13]. Additionally, Landsat 8 satellite image data can be collected regularly which enables the monitoring of drought over time and the assessment of its impacts on vegetation and the environment [14].…”

Section: Introductionmentioning

confidence: 99%

Building drought classification map with landsat 8 image data in Bac Binh district, Binh Thuan province

Dieu Chinh,

Hang,

Quynh

et al. 2023

STCE

View full text Add to dashboard Cite

Vietnam experiences increasing droughts throughout the dry season due to climate change, global warming,and human-caused activities like urbanization and deforestation. Drought hazard significantly impacts socioeconomic, agriculture, and the environment; it directly threatens human lives, livelihoods, food security, and environmental degradation. It is essential to have a drought assessment map to assist in developing and implementing strategies to combat drought. Space remote sensing technology development has enabled efficient and cost-effective monitoring and evaluation of droughts on a large scale, surpassing the capabilities of ground-based observations. This research uses remote sensing technology to monitor and assess the severity of the drought in the Bac Binh district, Binh Thuan province. We analyzed the Temperature Vegetation Dryness Index (TVDI) using multi-temporal Landsat 8 satellite data for the severe drought events in 2014, 2017, and 2020. The results indicate a significant increase in the percentage of land area affected by drought, from 50.74% in 2014 to 66.23% in 2020. The obtained maps provide valuable visual data to relevant agencies, assisting with planning preventative measures and mitigating future drought risks.

show abstract

Bamboo Forest Mapping in China Using the Dense Landsat 8 Image Archive and Google Earth Engine

Cited by 32 publications

References 62 publications

Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery

Analysis of the Coupled Assessment of Ecosystem Health and Its Spatial and Temporal Evolution in Fujian China

Building drought classification map with landsat 8 image data in Bac Binh district, Binh Thuan province

Contact Info

Product

Resources

About