Risk assessment and validation of farmland abandonment based on time series change detection

Chen, Hang; Tan, Yinuo; Xiao, Wu; Xu, Suchen; Meng, Fei; He, Tingting; Li, Xinhui; Wang, Kechao; Wu, Shaoen

doi:10.1007/s11356-022-22361-w

Cited by 7 publications

(7 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Meanwhile, based on indicators from agri-environmental indicators, combining spatial analysis method and agent-based modeling (e.g., Dyna-Clue, GeoSOS-FLUS, and CLUE-S), the distribution of future abandoned cropland under different scenarios was predicted in various regions (Das et al, 2019;Hu et al, 2013;Kai et al, 2020). These studies demonstrate the advantages of CAR evaluation in integrating various data and methodologies to forecast CA's spatio-temporal pattern and trend (Chen, Tan, et al, 2023;Terres et al, 2015). However, its major limitation is that the evaluation should be limited to the specific administrative boundary and cannot track the status of the cropland at the parcel level (Milenov et al, 2014;.…”

Section: Introductionmentioning

confidence: 79%

“…CA is an observed phenomenon that has already occurred or is occurring, which is determined by various elements at the regional, patch, and household levels (Corbelle‐Rico & Crecente‐Maseda, 2014; Terres et al, 2015; Ustaoglu & Collier, 2018). Therefore, it is possible to integrate and weigh these key driving indicators of CA to detect CAR (Chen, Tan, et al, 2023). By comparing the CAR index across different regions, households, or patches, we can identify the areas or units where CA is prone to occur.…”

Section: Methodsmentioning

confidence: 99%

“…For example, the European Union developed 35 agri‐environmental indicators to monitor agri‐environmental issues at the national levels (Milenov et al, 2014; Schulte et al, 2019). Moreover, a CAR indicator, called “identification of the risk of Farmland abandonment” (Nr 14), calculated by national‐level statistical data and land use dataset, was included in agri‐environmental indicators (Pawlewicz & Pawlewicz, 2023; Chen, Tan, et al, 2023). This indicator index was successfully applied to evaluate the CAR in 27 European Union countries and provided valuable insights for reducing CA (Valujeva et al, 2022; Terres et al, 2015), which has also been adopted to conduct CAR studies in China at regional and county scale, such as in the Yangtze River Economic Belt, the mountainous areas of Chongqing (Chen, Tan, et al, 2023; Guo & Song, 2019; Su et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, a CAR indicator, called “identification of the risk of Farmland abandonment” (Nr 14), calculated by national‐level statistical data and land use dataset, was included in agri‐environmental indicators (Pawlewicz & Pawlewicz, 2023; Chen, Tan, et al, 2023). This indicator index was successfully applied to evaluate the CAR in 27 European Union countries and provided valuable insights for reducing CA (Valujeva et al, 2022; Terres et al, 2015), which has also been adopted to conduct CAR studies in China at regional and county scale, such as in the Yangtze River Economic Belt, the mountainous areas of Chongqing (Chen, Tan, et al, 2023; Guo & Song, 2019; Su et al, 2022). Meanwhile, based on indicators from agri‐environmental indicators, combining spatial analysis method and agent‐based modeling (e.g., Dyna‐Clue, GeoSOS‐FLUS, and CLUE‐S), the distribution of future abandoned cropland under different scenarios was predicted in various regions (Das et al, 2019; Hu et al, 2013; Kai et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Assessing and mapping cropland abandonment risk in China

Zeng,

Luo,

Chen

et al. 2024

Land Degrad Dev

View full text Add to dashboard Cite

Cropland abandonment (CA) in China worsens the human‐land conflict and endangers national food sustainability. Scientifically assessing cropland abandonment risk (CAR) can provide valuable information for early warning and prevention of CA. Despite the extensive literature on the identification, determinants, and consequences of CA, the research on CAR still needs to be improved, especially on a grid scale. Therefore, this study constructed an evaluation indicators system regarding farming conditions, socio‐economic, and patch characteristics and used optimal parametric geographical detector and structural equation modeling to assess the CAR in China from 2010 to 2020. The results show China's CAR decreased from west to east. Very high and high CAR areas were in plateaus and mountains in western China. Medium CAR areas were mainly in central and southeastern China. Very low and low CAR areas were mainly in the Sichuan Basin and eastern plains. In 2010, the high and medium CARs accounted for a larger share of the area, 24.814% and 24.759%, respectively. The area share of very low, low, and very high CAR was 19.294%, 19.501%, and 11.633%, respectively. By 2020, both low and very high CARs increased, while the opposite was true for other grades of CAR. Very high CAR increased most evidently in the Loess Plateau. Although high CAR decreased, 43,327 km2 of medium CAR was converted to high CAR. CAR's centers of gravity in China were located at the junction of the Loess Plateau and the Huang‐Huai‐Hai Plain and have shifted to the northwest by 5445.34 m. The findings will assist stakeholders in developing targeted cropland protection strategies to prevent CA and efficiently allocate resources for agricultural production.

show abstract

Section: Introductionmentioning

confidence: 79%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Assessing and mapping cropland abandonment risk in China

Zeng,

Luo,

Chen

et al. 2024

Land Degrad Dev

View full text Add to dashboard Cite

show abstract

“…This forces to focus on lands are not used for agricultural purposes for a long time or to return non-contaminated and slightly destructed abandoned fields to agricultural use. Currently, debate on economic benefit of returning of abandoned lands in agricultural turnover are still going on [13][14][15]. However, over the past 10-12 years, in Bryansk Oblast a course to decreasing of agricultural land abandonment has been implemented.…”

Section: Discussionmentioning

confidence: 99%

Transformation of ecosystems in Bryansk Oblast caused by the agro-industrial complex development

Некрич

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The article outlines the location, scales, and intensity of the current ecosystems transformation due to operation of the agro-industrial complex industries in Bryansk Oblast of the Russian Federation. By means of official statistic data and space images gathered from open sources, the key factors determining the environmental condition of agricultural landscapes are identified. For each agricultural landscape’s units, a detailed description is given. Analysis of the current environmental situation within these units is also conducted. It was determined that over the last 12 years, the severe level of ecosystems transformation has been forming in the central and eastern parts of agricultural lands. The significant level of ecosystems transformation is observed in the north, as well as in the eastern and southwestern parts. The moderate level of ecosystems transformation is mostly common on the western part and is located in the central and eastern parts of agricultural lands. The minor level of ecosystems transformation is typical for the south-central and for the north-central parts of agricultural lands. The study shows that the spatial differentiation of the levels of ecosystems transformation in Bryansk Oblast is strongly determined by environmental conditions, the structure of natural landscapes, and depends on the specifics of agriculture.

show abstract

Forestry Ecosystem Protection from the Perspective of Eco-civilization Based on Self-Attention Using Hierarchical Dilated Convolutional Neural Network

Meng

2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

Ensuring the sustainable protection of forestry ecosystems faces numerous challenges. One significant hurdle is the constant threat of illegal logging and deforestation. Despite various regulations and conservation efforts, enforcing these measures can be difficult, particularly in remote or poorly monitored areas. Additionally, the increasing global demand for timber and other forest products puts immense pressure on these ecosystems, leading to overexploitation and habitat degradation. In this manuscript, Self-Focused Hierarchical Augmented Convolution Neural Network (SAHD-CNN) optimized with Tasmanian Devil Optimization (TDO) algorithm is proposed. Initially data is taken from Global Leaf Area Index (LAI) dataset. Afterward the input data is fed to Adaptive Distorted Quantum Matched-Filter. The pre-processing output is provided to Self-Focused Hierarchical Augmented Convolution Neural Network (SAHD-CNN) to effectively classifying Forestry Ecosystem Protection (FEP) for high, medium, and low. The weight parameters of the SAHD-CNN are optimized using Tasmanian Devil (TD) Optimization method. The proposed method is implemented in MATLAB working platform. The FEP-SAHDCNN technique attains higher accuracy value of 99% than the existing techniques such as Forestry Ecosystem Protection based Particle swarm Optimization (FEP-PSO) Accuracy value is 65%, Forestry Ecosystem Protection using Evaluation-based Neural Network (FEP-EN) Accuracy value is 82%, and FEP-GRS Accuracy value is 79%. Thus, the proposed method gives optimal output than the existing methods.

show abstract

Risk assessment and validation of farmland abandonment based on time series change detection

Cited by 7 publications

References 81 publications

Assessing and mapping cropland abandonment risk in China

Assessing and mapping cropland abandonment risk in China

Transformation of ecosystems in Bryansk Oblast caused by the agro-industrial complex development

Forestry Ecosystem Protection from the Perspective of Eco-civilization Based on Self-Attention Using Hierarchical Dilated Convolutional Neural Network

Contact Info

Product

Resources

About