Analysing the relationship between drought and soil erosion using vegetation health index and RUSLE models in Godavari middle sub-basin,India

Drought is a natural phenomenon posing severe implications for soil,groundwater and agricultural yield.It has been recognized as one of the most pervasive global change drivers to affect the soil.Soil being a weakly renewable resource takes a long time to form,but it takes no time to degrade.However,the response of soil to drought conditions as soil loss is not manifested in the existing literature.Thus,this study makes a concerted effort to analyze the relationship between drought conditions and soil erosion in the middle sub-basin of the Godavari River in India.MODIS remote sensing data was utilized for driving drought indices during 2000-2019.Firstly,we constricted Temperature condition index(TCI)and Vegetation Condition Index(VCI)from Land Surface Temperature(LST)and Enhanced Vegetation Index(EVI)derived from MODIS data.TCI and VCI were then integrated to determine the Vegetation Health Index(VHI).Revised Universal Soil Loss Equation(RUSLE)was utilized for estimating soil loss.The relationship between drought condition and vegetation was ascertained using the Pearson correlation.Most of the northern and southern watersheds experienced severe drought condition in the sub-basin during2000-2019.The mean frequency of the drought occurrence was 7.95 months.The average soil erosion in the sub-basin was estimated to be 9.88 t ha^(-1)year^(-1).A positive relationship was observed between drought indices and soil erosion values(r value being 0.35).However,wide variations were observed in the distribution of spatial correlation.Among various factors,the slope length and steepness were found to be the main drivers of soil erosion in the sub-basin.Thus,the study calls for policy measures to lessen the impact of drought and soil erosion.

Ensemble machine learning models based on Reduced Error Pruning Tree for prediction of rainfall-induced landslides

In this paper,we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree(REPT)as a base classifier with the Bagging(B),Decorate(D),and Random Subspace(RSS)ensemble learning techniques for spatial prediction of rainfallinduced landslides in the Uttarkashi district,located in the Himalayan range,India.To do so,a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets.Root Mean Square Error(RMSE)and Area Under the receiver operating characteristic Curve(AUC)were used to evaluate the training and validation performances of the models.The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides.The D-REPT model with RMSE=0.351 and AUC=0.907 was identified as the most accurate model,followed by RSS-REPT(RMSE=0.353 and AUC=0.898),B-REPT(RMSE=0.396 and AUC=0.876),and the single REPT model(RMSE=0.398 and AUC=0.836),respectively.The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world.