Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland: A case‐study in Syria

Mohammed, Safwan; Jouhra, Ali; Enaruvbe, Glory O.; Bashir, Bashar; Barakat, Mona Mohamed; Alsilibe, Firas; Kulimushi, Luc Cimusa; Alsalman, Abdullah; Szabó, Szilárd

doi:10.1002/ldr.4655

Cited by 7 publications

(2 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While many studies have compared the performance of individual ML models in mapping soil erosion (Nguyen et al, 2021, Fernández et al, 2023, Mohammed et al, 2023, there has been little exploration of combining models to enhance overall predictive performance. This approach is known as ensemble learning.…”

Section: Ensemble Strategymentioning

confidence: 99%

Mapping Soil Erosion Classes using Remote Sensing Data and Ensemble Models

Oraegbu,

Jolaiya

2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Soil loss by water erosion is projected to increase by 13 – 22.5% in the European Union (EU) and United Kingdom (UK) by 2050, leading to loss of cultivable land and soil structure degradation. Accurate mapping of soil erosion is crucial for identifying vulnerable areas and implementing sustainable land management practices. In this study, we introduce machine learning (ML) models to map soil erosion, leveraging their capabilities in categorical mapping. Unlike previous applications that primarily mapped the absence or presence of a soil erosion class, we propose an ensemble strategy using three ML ensemble models (CatBoost, LightGBM, XGBoost) with remote sensing data to map four classes of soil erosion (i.e No Gully/badland, Gully, Badland, Land-slides). The proposed model effectively captures spatiotemporal variations over Europe in the period of 2000 – 2022, with particular precision in mapping Land-slides. The proposed method advances soil erosion mapping across different spatial and temporal scales particularly in the EU, contributing to the development of targeted conservation strategies and sustainable land management practices.

show abstract

Section: Ensemble Strategymentioning

confidence: 99%

Mapping Soil Erosion Classes using Remote Sensing Data and Ensemble Models

Oraegbu,

Jolaiya

2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…where y is the dependent variable (the outcome) predicted by the function f(x), α is the model intercept, and β i is the coefficient of the hi basis functions given the N number of base functions. For other information about the method, please refer to [6,27,35,[47][48][49]. For this research, MARS analysis was performed using the "earth" R-package [50].…”

Section: Statistical Model Validation Tools and Model-building Strate...mentioning

confidence: 99%

Using Public Landslide Inventories for Landslide Susceptibility Assessment at the Basin Scale: Application to the Torto River Basin (Central-Northern Sicily, Italy)

Martinello,

Mercurio,

Cappadonia

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In statistical landslide susceptibility evaluation, the quality of the model and its prediction image heavily depends on the quality of the landslide inventories used for calibration. However, regional-scale inventories made available by public territorial administrations are typically affected by an unknown grade of incompleteness and mapping inaccuracy. In this research, a procedure is proposed for verifying and solving such limits by applying a two-step susceptibility modeling procedure. In the Torto River basin (central-northern Sicily, Italy), using an available regional landslide inventory (267 slide and 78 flow cases), two SUFRA_1 models were first prepared and used to assign a landslide susceptibility level to each slope unit (SLU) in which the study area was partitioned. For each of the four susceptibility classes that were obtained, 30% of the mapping units were randomly selected and their stable/unstable status was checked by remote analysis. The new, increased inventories were finally used to recalibrate two SUFRA_2 models. The prediction skills of the SUFRA_1 and SUFRA_2 models were then compared by testing their accuracy in matching landslide distribution in a test sub-basin where a high-resolution systematic inventory had been prepared. According to the results, the strong limits of the SUFRA_1 models (sensitivity: 0.67 and 0.57 for slide and flow, respectively) were largely solved by the SUFRA_2 model (sensitivity: 1 for both slide and flow), suggesting the proposed procedure as a possibly suitable modeling strategy for regional susceptibility studies.

show abstract

Artificial Intelligence Algorithms in Flood Prediction: A General Overview

Pandey

2024

Geo-Information for Disaster Monitoring and Management

View full text Add to dashboard Cite

Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland: A case‐study in Syria

Cited by 7 publications

References 77 publications

Mapping Soil Erosion Classes using Remote Sensing Data and Ensemble Models

Mapping Soil Erosion Classes using Remote Sensing Data and Ensemble Models

Using Public Landslide Inventories for Landslide Susceptibility Assessment at the Basin Scale: Application to the Torto River Basin (Central-Northern Sicily, Italy)

Artificial Intelligence Algorithms in Flood Prediction: A General Overview

Contact Info

Product

Resources

About