Estimation of soil erosion using RUSLE modeling and geospatial tools in a tea production watershed (Chisheke in Walungu), eastern Democratic Republic of Congo

Chuma, Géant Basimine; Bora, Francine Safina; Ndeko, Adrien Byamungu; Mugumaarhahama, Yannick; Cirezi, Nadège Cizungu; Mondo, Jean M.; Bagula, Espoir Mukengere; Karume, Katcho; Mushagalusa, Gustave Nachigera; Schimtz, Serge

doi:10.1007/s40808-021-01134-3

Cited by 20 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model was developed based on the concept of support vector machine (SVM), which is generally used in solving problems through regression and classification approaches [ 9 , 20 , 21 , 22 , 23 ]. SVR is an established computational technique with various merits, such as good noise-toleration, superior generalization ability, and high learning speed [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

Novel Hybridized Computational Paradigms Integrated with Five Stand-Alone Algorithms for Clinical Prediction of HCV Status among Patients: A Data-Driven Technique

Madaki

Abacıoğlu

Usman

et al. 2022

Life

View full text Add to dashboard Cite

The emergence of health informatics opens new opportunities and doors for different disease diagnoses. The current work proposed the implementation of five different stand-alone techniques coupled with four different novel hybridized paradigms for the clinical prediction of hepatitis C status among patients, using both sociodemographic and clinical input variables. Both the visualized and quantitative performances of the stand-alone algorithms present the capability of the Gaussian process regression (GPR), Generalized neural network (GRNN), and Interactive linear regression (ILR) over the Support Vector Regression (SVR) and Adaptive neuro-fuzzy inference system (ANFIS) models. Hence, due to the lower performance of the stand-alone algorithms at a certain point, four different novel hybrid data intelligent algorithms were proposed, including: interactive linear regression-Gaussian process regression (ILR-GPR), interactive linear regression-generalized neural network (ILR-GRNN), interactive linear regression-Support Vector Regression (ILR-SVR), and interactive linear regression-adaptive neuro-fuzzy inference system (ILR-ANFIS), to boost the prediction accuracy of the stand-alone techniques in the clinical prediction of hepatitis C among patients. Based on the quantitative prediction skills presented by the novel hybridized paradigms, the proposed techniques were able to enhance the performance efficiency of the single paradigms up to 44% and 45% in the calibration and validation phases, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Novel Hybridized Computational Paradigms Integrated with Five Stand-Alone Algorithms for Clinical Prediction of HCV Status among Patients: A Data-Driven Technique

Madaki

Abacıoğlu

Usman

et al. 2022

Life

View full text Add to dashboard Cite

show abstract

“…Both natural and anthropogenic factors are mentioned as the driving forces behind the gullying process. Anthropogenic activities favoring gullying include unplanned agriculture (Ollobarren Del Barrio et al, 2018), grazing activity (Higaki et al, 2020), infrastructural development (Imwangana et al, 2015), and deforestation (Chuma et al, 2021a(Chuma et al, , 2021b. Generally, gully erosion and its areal extension is a natural process fully controlled by external forces and shaped by internal settings.…”

Section: Introductionmentioning

confidence: 99%

“…One of the decisions was to manage the land degradation process at the watershed scale to emphasize management and decision-making. Soil water management has been studied at a watershed scale in several case studies (Chuma, 2019;Heri-Kazi, 2020;Chuma et al, 2021aChuma et al, , 2021bChuma et al, , 2022 in South-Kivu; only a few focused on the gullying process (Chuma et al, 2021a(Chuma et al, , 2021b. For the Luzinzi watershed, the gully erosion process has been studied by Chuma et al (2021a) by characterizing and determining driving factors.…”

Section: Introductionmentioning

confidence: 99%