Land degradation risk dynamics assessment in red and lateritic zones of eastern plateau, India: A combine approach of K-fold CV, data mining and field validation

被引:30
作者
Saha, Asish [1 ]
Pal, Subodh Chandra [1 ]
Chowdhuri, Indrajit [1 ]
Islam, Abu Reza Md. Towfiqul [2 ]
Roy, Paramita [1 ]
Chakrabortty, Rabin [1 ]
机构
[1] Univ Burdwan, Dept Geog, Bardhaman 713104, West Bengal, India
[2] Begum Rokeya Univ, Dept Disaster Management, Rangpur 5400, Bangladesh
关键词
Red and lateritic agro-climatic zones; Soil erosion; Land degradation; K-fold cross validation; Boosting-REPTree; Ex-situ plant species; LANDSLIDE SUSCEPTIBILITY ASSESSMENT; LOGISTIC-REGRESSION; SOIL-EROSION; WATER; DESERTIFICATION; PRODUCTIVITY; INDICATORS; PREDICTION; MODELS; AREAS;
D O I
10.1016/j.ecoinf.2022.101653
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
The phenomenon of land degradation is a serious environmental issue that affects many countries worldwide, particularly in the developing countries of sub-tropical regions like India. The assessment of land degradation is necessary for designing a mitigation plan that will reduce the adverse effects of land degradation. Recently, sensitivity models for analyzing land degradation have become a popular scientific tool for determining the spatial characteristics of this complicated environmental phenomenon. The objective of the current study is to prepare land degradation susceptibility maps for the gravely undulating red and lateritic agro-climatic zones (ACZ) of the Eastern plateau, India using hybrid techniques, i.e., integration of K-Fold cross-validation (CV) and machine learning algorithms of Reduced Error Pruning Tree (REPTree) and the ensemble of Bagging-REPTree and Boosting-REPTree. For the modelling purpose, sixteen independent land degradation conditioning factors were selected based on a multi-collinearity test, and dependent factors, i.e., gully and ravine points, were collected from published reports and field investigations. The evaluation result of the models indicates that Boosting-REPTree is the most optimal in prediction analysis, as the area under the curve (AUC) of training and validation is 0.944 and 0.928, respectively, in K-Fold 1 followed by Bagging-REPTree and REPTree. As a result, this study suggested that the ensemble of the Boosting-REPTree model can be applied as a new potential method for spatial prediction of land degradation in future research. The study also revealed that ex-situ plant species had been adopted to control soil erosion. Still, it is considered a false measure as ex-situ plant species cannot prevent erosion to an optimal level. Overall, a land degradation prevention planning map has also been suggested to measure soil erosion.
引用
收藏
页数:19
相关论文
共 99 条
  • [61] Classification Efficacy Using K-Fold Cross-Validation and Bootstrapping Resampling Techniques on the Example of Mapping Complex Gully Systems
    Phinzi, Kwanele
    Abriha, David
    Szabo, Szilard
    [J]. REMOTE SENSING, 2021, 13 (15)
  • [62] Pourghasemi HR, 2020, ADV SCI TECHNOL INN, P415, DOI 10.1007/978-3-030-23243-6_28
  • [63] Pourghasemi HR., 2012, TERRIGENOUS MASS MOV, P23, DOI [10.1007/978-3-642-25495-6_2, DOI 10.1007/978-3-642-25495-6_2]
  • [64] Spatial assessment of land sensitivity to degradation across Romania. A quantitative approach based on the modified MEDALUS methodology
    Pravalie, Remus
    Patriche, Cristian
    Savulescu, Ionut
    Sirodoev, Igor
    Bandoc, Georgeta
    Sfica, Lucian
    [J]. CATENA, 2020, 187
  • [65] Mapping and assessment of degraded land in the Heihe River Basin, arid northwestern China
    Qi, Shanzhong
    Cai, Yumin
    [J]. SENSORS, 2007, 7 (11) : 2565 - 2578
  • [66] SIMPLIFYING DECISION TREES
    QUINLAN, JR
    [J]. INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1987, 27 (03): : 221 - 234
  • [67] Contribution of physical and anthropogenic factors to gully erosion initiation
    Rahmati, Omid
    Kalantari, Zahra
    Ferreira, Carla Sofia
    Chen, Wei
    Soleimanpour, Seyed Masoud
    Kapovic-Solomun, Marijana
    Seifollahi-Aghmiuni, Samaneh
    Ghajarnia, Navid
    Kazemabady, Nader Kazemi
    [J]. CATENA, 2022, 210
  • [68] Groundwater spring potential modelling: Comprising the capability and robustness of three different modeling approaches
    Rahmati, Omid
    Naghibi, Seyed Amir
    Shahabi, Himan
    Dieu Tien Bui
    Pradhan, Biswajeet
    Azareh, Ali
    Rafiei-Sardooi, Elham
    Samani, Aliakbar Nazari
    Melesse, Assefa M.
    [J]. JOURNAL OF HYDROLOGY, 2018, 565 : 248 - 261
  • [69] Ricci GF, 2020, LAND USE POLICY, V90, DOI [10.1016/j.landusepol.2019.104306, 10.1016/j.la]
  • [70] ASSESSMENT OF MULTICOLLINEARITY - HAITOVSKY TEST OF DETERMINANT
    ROCKWELL, RC
    [J]. SOCIOLOGICAL METHODS & RESEARCH, 1975, 3 (03) : 308 - 320