Centre de documentation
scientifique

Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India / Sunil Saha in Geomatics, Natural Hazards and Risk, vol 12 n° 1 (2021)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 12 n° 1 (2021) . - pp 29 - 62 Titre : Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India Type de document : Article/Communication Auteurs : Sunil Saha, Auteur ; Gopal Chandra, Auteur ; Biswajeet Pradhan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 29 - 62 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] changement d'occupation du sol [Termes IGN] classification hybride [Termes IGN] classification par Perceptron multicouche [Termes IGN] déboisement [Termes IGN] ensachage [Termes IGN] Inde [Termes IGN] modèle de simulation [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] Rotation Forest classification [Termes IGN] système d'information géographique Résumé : (auteur) The rapid expansion of human settlement, agricultural land and roads because of population growth in several regions of the world has contributed to the depletion of forest land. In this study, novel ensemble intelligent approaches using bagging, dagging and rotation forest (RTF) as meta classifiers of multilayer perceptron (MLP) were used to predict spatial deforestation probability (DP) in Gumani Basin, India. The success rate and correctness of prediction of the ensemble models were compared with MLP. A total of 1000 deforested pixels and 14 deforestation determining factors (DDFs) were used. The ensemble models were trained using 70% of the deforested pixels and validated with the remaining 30%. DDFs were chosen by applying the information gain ratio and Relief-F test methods. Distance to settlement, population growth and distance to roads were the most important factors. The results of DP modelling demonstrated that nearly 16.82%–12.64% of the basin had very high DP. All four models created DP maps with reasonable prediction accuracy and goodness of fit, but the best map was produced by MLP-bagging. The accuracy of the MLP neural net model was increased 2-3% after ensemble with the hybrid meta classifiers (RTF, bagging and dagging). The proposed method could be used for deforestation prediction in other areas having similar geo-environmental conditions. Furthermore, the findings might be used as a basis for future research and could help planners in forest management. Numéro de notice : A2021-106 Affiliation des auteurs : non IGN Thématique : FORET/INFORMATIQUE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/19475705.2020.1860139 Date de publication en ligne : 22/12/2020 En ligne : https://doi.org/10.1080/19475705.2020.1860139 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96903 [article]

Soil erosion assessment using RUSLE model and its validation by FR probability model / Amiya Gayen in Geocarto international, vol 35 n° 15 ([01/11/2020])  

Public [article]  inGeocarto international > vol 35 n° 15 [01/11/2020] . - pp 1750 - 1768 Titre : Soil erosion assessment using RUSLE model and its validation by FR probability model Type de document : Article/Communication Auteurs : Amiya Gayen, Auteur ; Sunil Saha, Auteur ; Hamid Reza Pourghasemi, Auteur Année de publication : 2020 Article en page(s) : pp 1750 - 1768 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse de sensibilité [Termes IGN] cartographie des risques [Termes IGN] érosion [Termes IGN] érosion hydrique [Termes IGN] fréquence [Termes IGN] Inde [Termes IGN] modèle RUSLE [Termes IGN] modèle stochastique [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] occupation du sol [Termes IGN] pente [Termes IGN] surveillance géologique [Termes IGN] utilisation du sol Résumé : (auteur) The objective of the current study is to estimate the annual average soil loss through RUSLE model and furthermore assess the soil erosion risk and its distribution using frequency ratio (FR) probability algorithm. At first, soil erosion risk zones were identified using FR model by the consideration 14 soil erosion conditioning factors such as land use (LU/LC), slope, slope aspect, normalized difference vegetation index (NDVI), altitude, plan curvature, stream power index, distance from river, road, and lineament, soil types, rainfall erosivity, slope length and lineament density. Secondly, the spatial pattern of annual average soil loss rates was estimated using RUSLE model with consideration of five factors such as, rainfall erosivity (R), cover management (C), slope length (LS), soil erodability (K), and conservation practice factors (P). In order to map soil erosion susceptibility by the FR model, dataset divided randomly into parts 70/30 percent for training and validation purposes, respectively. Based on the FR value, the susceptibility map was reclassified into five different critical erosion probability zones. Among this, the severe and high erosion zones occupy 13.69% and 16.26%, respectively, of the total area, where as low and very low susceptibility zones together constitute 32.98% of the River Basin. The assessed high amount of average annual soil erosion (more than 100 t/ha/year) is occupied 9.55% of the total study area. It is conclude that high soil erosion susceptibility and yearly average soil loss were performed in this study area. Therefore, the produced soil erosion susceptibility maps and annual average soil erosion map can be very useful for primary land use planning and soil erosion hazard mitigation purpose for prioritizing areas. Numéro de notice : A2020-660 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1581272 Date de publication en ligne : 21/03/2019 En ligne : https://doi.org/10.1080/10106049.2019.1581272 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96134 [article]