The Influence of Climate Change and Socioeconomic Transformations on Land Use and NDVI in Ordos, China DOI Creative Commons
Yin Cao, Zhigang Ye, Yuhai Bao

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1489 - 1489

Published: Dec. 13, 2024

Land use change is related to a series of core issues global environmental change, such as quality improvement, sustainable utilization resources, energy reuse and climate change. In this study, Google Earth Engine (GEE), remote sensing natural environment monitoring analysis platform, was used realize the combination Landsat TM/OLI data images with spectral features topographic features, random forest machine learning classification method supervise classify low-cloud composite image Ordos City. The results show that: (1) GEE has powerful computing function, which can efficient high-precision in-depth long-term multi-temporal land accuracy acquisition reach 87%. Compared other sets in same period, overall local are more distinct than ESRI (Environmental Systems Research Institute) GlobeLand 30 products. Slightly lower Institute Aerospace Information Innovation Chinese Academy Sciences obtain m cover fine (2) City from 2003 2023 between 79–87%, Kappa coefficient 0.79–0.84. (3) Climate, terrain, population interactive factors combined socio-economic national policies main affecting 2023.

Language: Английский

Land-Use Change Dynamics in Areas Subjected to Direct Urbanization Pressure: A Case Study of the City of Olsztyn DOI Open Access
Andrzej Biłozor, Iwona Cieślak, Szymon Czyża

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(7), P. 2923 - 2923

Published: March 31, 2024

Urbanization is one of the most visible symptoms global changes. This process has been driven by evolution life on Earth, and it gradually modifies structure land use. Urban development apparent indicator measure urbanization. The demand for vacant sustainable spatial plans require new methods that support decision-making in changing use suburban areas. aim this study was to describe a methodology identifying localizing urban boundaries with fuzzy set theory, evaluate degree urbanization, analyze dynamics land-use changes areas subjected direct urbanization pressure photogrammetric data 2005, 2010, 2017, 2022. A case conducted Polish city Olsztyn. study’s results determined [0, 1] range, as well change each twenty-four adopted forms indicate proposed are useful rate direction can be applied optimize counterbalance settlements infrastructure.

Language: Английский

Citations

5
Leveraging machine learning for intelligent agriculture DOI Creative Commons

B. J. Sowmya,

A. K. Meeradevi,

S Supreeth

et al.

Discover Internet of Things, Journal Year: 2025, Volume and Issue: 5(1)

Published: March 26, 2025

Language: Английский

Citations

0
Detailed Land Use Classification in a Rare Earth Mining Area Using Hyperspectral Remote Sensing Data for Sustainable Agricultural Development DOI Open Access
Chige Li, Hengkai Li, Yanbing Zhou

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(9), P. 3582 - 3582

Published: April 24, 2024

In China, ion-adsorbing rare earth minerals are mainly located in the southern hilly areas and important strategic resources. Extensive long-term mining has severely damaged land cover areas, caused soil pollution terrain fragmentation, disrupted balance between agriculture, restricted agricultural development, affected ecological development. Precise detailed classification of use within is crucial for monitoring sustainable development ecology these areas. this study, we leverage high spatial spectral resolution characteristics Zhuhai-1 (OHS) hyperspectral image datasets. We create four types datasets based on spectral, vegetation, red edge, texture characteristics. These optimized multifaceted features, considering complex scenario Additionally, design seven optimal combination schemes features. This performed to examine impact different accuracy identifying classes from broken blocks. The results show that (1) inclusion features most obvious effect overall accuracy; (2) edge feature worst improving surface classification; however, it a prominent identification lands such as farmland, orchards, reclaimed vegetation; (3), following various optimization yielded highest accuracy, at 88.16%. Furthermore, comprehensive classes, including greenhouse vegetables, desirable outcomes. research not only highlight advantages images recognition but also address previous limitations application over wide underscore reliability selection methods reducing information redundancy accuracy. proposed combination, OHS datasets, offers technical support guidance accurate agroecological environments.

Language: Английский

Citations

2
An OVR-FWP-RF Machine Learning Algorithm for Identification of Abandoned Farmland in Hilly Areas Using Multispectral Remote Sensing Data DOI Open Access

L. Wang,

Qian Li,

Youhan Wang

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(15), P. 6443 - 6443

Published: July 27, 2024

Serious farmland abandonment in hilly areas, and the resolution of commonly used satellite-borne remote sensing images are insufficient to meet needs identifying abandoned such regions. Furthermore, addressing problem areas with a certain level accuracy is crucial issue research extracting information on patches from images. Taking typical village as an example, this study utilizes airborne multispectral images, incorporating various feature factors spectral characteristics texture features. Aiming at method for based OVR-FWP-RF algorithm proposed. two machine learning algorithms, Random Forest (RF) XGBoost, also utilized comparison. The results indicate that overall (OA) OVR-FWP-RF, Forest, XGboost classification algorithms have reached 92.66%, 90.55%, 90.75%, respectively, corresponding Kappa coefficients 0.9064, 0.8796, 0.8824. Therefore, by combining features, vegetation factors, use methods can improve ground objects. Moreover, outperforms XGboost. Specifically, when using identify farmland, its producer (PA) 3.22% 0.71% higher than XGboost, while user (UA) 5.27% 6.68% higher, respectively. significantly identification other land type recognition providing new well useful reference similar areas.

Language: Английский

Citations

0
Mapping cropland in Yunnan Province during 1990–2020 using multi-source remote sensing data with the Google Earth Engine Platform DOI Creative Commons
M. Wang, Liang Huang, Bo‐Hui Tang

et al.

Geocarto International, Journal Year: 2024, Volume and Issue: 39(1)

Published: Jan. 1, 2024

Language: Английский

Citations

0
The Influence of Climate Change and Socioeconomic Transformations on Land Use and NDVI in Ordos, China DOI Creative Commons
Yin Cao, Zhigang Ye, Yuhai Bao

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1489 - 1489

Published: Dec. 13, 2024

Land use change is related to a series of core issues global environmental change, such as quality improvement, sustainable utilization resources, energy reuse and climate change. In this study, Google Earth Engine (GEE), remote sensing natural environment monitoring analysis platform, was used realize the combination Landsat TM/OLI data images with spectral features topographic features, random forest machine learning classification method supervise classify low-cloud composite image Ordos City. The results show that: (1) GEE has powerful computing function, which can efficient high-precision in-depth long-term multi-temporal land accuracy acquisition reach 87%. Compared other sets in same period, overall local are more distinct than ESRI (Environmental Systems Research Institute) GlobeLand 30 products. Slightly lower Institute Aerospace Information Innovation Chinese Academy Sciences obtain m cover fine (2) City from 2003 2023 between 79–87%, Kappa coefficient 0.79–0.84. (3) Climate, terrain, population interactive factors combined socio-economic national policies main affecting 2023.

Language: Английский

Citations

0