Determining Cover Management Factor with Remote Sensing and Spatial Analysis for Improving Long-Term Soil Loss Estimation in Watersheds

Abstract

The universal soil loss equation (USLE) is a widely used empirical model for estimating soil loss. Among the USLE model factors, the cover management factor (C-factor) is a critical factor that substantially impacts the estimation result. Assigning C-factor values according to a land-use/land-cover (LULC) map from field surveys is a typical traditional approach. However, this approach may have limitations caused by the difficulty and cost in conducting field surveys and updating the LULC map regularly, thus significantly affecting the feasibility of multi-temporal analysis of soil erosion. To address this issue, this study uses data mining to build a random forest (RF) model between eight geospatial factors and the C-factor for the Shihmen Reservoir watershed in northern Taiwan for multi-temporal estimation of soil loss. The eight geospatial factors were collected or derived from remotely sensed images taken in 2004, a digital elevation model, and related digital maps. Due to the memory size limitation of the R software, only 4% of the total data points (population dataset) in each C-factor class were selected as the sample dataset (input dataset) for analysis using the stratified random sampling method. Seventy percent of the input dataset was used to train the RF model, and the other 30% was used to test the model. The results show that the RF model could capture the trend of vegetation recovery and soil loss reduction after the destructive event of Typhoon Aere in 2004 for multi-temporal analysis. Although the RF model was biased by the majority class’s large sample size (C = 0.01 class), the estimated soil erosion rate was close to the measurement obtained by the erosion pins installed in the watershed (90.6 t/ha-year). After the model’s completion, we furthered our aim to address the input dataset’s imbalanced data problem to improve the model’s classification performance. An ad-hoc down-sampling of the majority class technique was used to reduce the majority class’s sampling rate to 2%, 1%, and 0.5% while keeping the other minority classes at a 4% sample rate. The results show an improvement of the Kappa coefficient from 0.574 to 0.732, the AUC from 0.780 to 0.891, and the true positive rate of all minority classes combined from 0.43 to 0.70. However, the overall accuracy decreases from 0.952 to 0.846, and the true positive rate of the majority class declines from 0.99 to 0.94. The best average C-factor was achieved when the sampling rate of the majority class was 1%. On the other hand, the best soil erosion estimate was obtained when the sampling rate was 2%.

DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning

“…Nguyen et al [20] were the first to create machine learning models from field erosion pin measurements, a critical difference from other ML studies on soil erosion. The analysis was improved and expanded to different ML algorithms, including ensemble learning methods [21][22][23]. However, because some of the environmental factors used in the studies mentioned above were point data, the resulting models could not be directly applied to the entire study area (watershed) without interpolation.…”

Soil Erosion and Deposition in a Taiwanese Watershed Using USPED

“…On the one hand, there are seven categories of soil erosion: 0-1, 1-3, 3-5, 5-10, 10-20, 20-40, and >40 Mg/ha/year. Soil deposition, on the other hand, is divided into two catego- The Shihmen Reservoir watershed covers an area of approximately 760 km 2 . The overall topography slopes from south to north (from 3527 to 221 m above the mean sea level, as illustrated in Figure 1), with the reservoir lying on the northern end.…”

“…When analyzing soil erosion in a watershed, the universal soil loss equation (USLE) and the revised universal soil loss equation (RUSLE) are the most common models used by researchers around the world, accounting for 13.9% and 17.1% of the literature published between 1994 and 2017 in the Scopus database, respectively [1]. The predominant use of USLE and RUSLE is also true in Taiwan for soil erosion analysis [2][3][4][5][6][7][8][9][10][11]. However, USLE or RUSLE can only model the amount of soil erosion in watersheds; they cannot simulate the movement of sediments and where the soil is deposited in the watersheds.…”

“…Gross erosion was measured at 3.8 mm/year with a predicted rate of 2.1 mm/year. More recently, Gioia et al [15] utilized USPED to forecast the location of linear erosion in a 7 km 2 watershed in southern Italy's Apennines and discovered that the USPED model predicted the location of linear erosion quite reliably. Similarly, Domingues et al [16] used USPED and genetic algorithm to optimize the placement and size of forest restoration zones.…”

Multi-Decadal Assessment of Soil Loss in a Mediterranean Region Characterized by Contrasting Local Climates

“…Specifically, we chose the Soil-Adjusted Vegetation Index (SAVI), as proxy for canopy cover, see [50], since it has been proven to be strongly correlated with C factor as compared with other vegetation indices [51]. In particular, the SAVI has been demonstrated to be able to appropriately account for sparsely vegetated areas where, generally, the well-known Normalized Difference Vegetation Index (NDVI) is highly variable [52]. Following [53], we estimated the C factor as:…”