Related Experiment Video
Updated: Jan 13, 2026

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
Vegetation type dominates slope-scale material loss under extreme rainfall: Nonlinear responses revealed by machine
Aipu Wu1, Chunzi Ma1, Shouliang Huo2
1School of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150038, China; State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China.
Climate change intensifies extreme rainfall, increasing soil erosion and pollution. Vegetation type and rainfall intensity are key factors controlling material loss, with farmland being most vulnerable.
Area of Science:
- Environmental Science
- Hydrology
- Climate Change Impact
Background:
- Extreme rainfall events, intensified by climate change, threaten mountainous agricultural watersheds with soil erosion and non-point source (NPS) pollution.
- Understanding material losses under varying rainfall patterns is crucial for watershed management.
Purpose of the Study:
- To investigate the impact of extreme rainfall on slope-scale soil erosion and NPS pollution.
- To quantify material losses (soil, TN, TP, COD) under different vegetation and slope types.
- To identify dominant factors controlling material losses during extreme rainfall events.
Main Methods:
- Utilized seven years of field observations (2014-2020) from four runoff plots (farmland vs. shrubland, steep vs. gentle slopes).
- Employed a machine learning framework integrating Random Forest (RF) with Sequential Backward Selection (SBS) and relative importance (RI) analyses.
- Analyzed 61 runoff events, including 10 extreme rainfall events, based on rainfall depth and 30-min maximum intensity (I30).
Main Results:
- Extreme rainfall events (16.4% of total) contributed significantly to soil loss (41.9%) and COD (49.2%).
- Farmland plots exhibited 2-5 times greater material losses than shrubland plots during extreme rainfall.
- Vegetation type and 60-min rainfall intensity (I60) were dominant factors controlling losses under extreme rainfall.
Conclusions:
- Vegetation type plays a dominant role in controlling slope-scale material loss.
- Machine learning frameworks are effective in explaining complex hydrological processes and identifying critical material loss thresholds.
- Findings highlight the vulnerability of agricultural watersheds to extreme rainfall and underscore the importance of vegetation management.
Related Concept Videos
Survival Tree
Building a Survival Tree
Constructing a...
Responses to Drought and Flooding
Design Example: Maintaining Level of an Embankment
Adaptations that Reduce Water Loss
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Precipitation Gravimetry
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...

