通过机器学习和深度学习算法对土壤有机碳含量跨土地使用类型的变量分析及其数字绘制
Mounir Oukhattar1,2, Sébastien Gadal3,4, Yannick Robert5
1Aix-Marseille Univ., CNRS, ESPACE UMR 7300, Univ., Nice Sophia Antipolis, Avignon Univ., Aix-en-Provence, 13545, France. mounir.oukhattar@etu.univ-amu.fr.
Environmental monitoring and assessment
|April 10, 2025
概括
根据法国普罗旺斯的土地使用情况,土壤有机碳 (SOC) 差异很大,森林占地面积最多,耕地最少. 机器学习模型,特别是XGBoost,准确地预测SOC水平,帮助可持续的土地管理和气候变化缓解.
科学领域:
- 环境科学 环境科学
- 土壤科学 土壤科学
- 数据科学数据科学数据科学
背景情况:
- 土壤有机碳 (SOC) 对土壤肥力和碳循环管理至关重要.
- 了解 SOC 的空间变化对于有效地管理土壤资源至关重要.
- 法国东南部的普罗旺斯采矿盆地为研究SOC动态提供了一个独特的景观.
研究的目的:
- 在11种土地使用类型中分析和建模SOC含量的空间变化.
- 确定影响SOC分布的关键环境因素.
- 评估用于SOC预测的机器和深度学习算法的性能.
主要方法:
- 收集了162个土壤样本和21个环境共变量 (气候,石质,地形,土地覆盖,遥感,土壤特性).
- 应用了四种回归算法:随机森林 (RF),支持向量机 (SVM),极端梯度增强 (XGBoost) 和深度神经网络 (DNNs).
- 使用集成数据和算法进行空间建模的SOC可变性.
主要成果:
- 在土地用途中观察到SOC含量的显著变化,森林 (69.3g/kg) 最高,耕地 (8.9g/kg) 最低.
- 土地覆盖面,地形,石质,环境指数和粘土含量被确定为SOC的主要驱动因素.
- XGBoost实现了最高的预测准确度 (R2 = 0.73),其次是RF (R2 = 0.68) 和DNN (R2 = 0.60).
结论:
- XGBoost和RF模型提供可靠和高效的SOC预测,即使数据有限.
- 这些发现为优化法国东南部土壤有机碳管理提供了关键的见解.
- 这项研究通过可持续的土地管理实践支持气候变化减缓战略.
更多相关视频
相关概念视频
Variability: Analysis
116
Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...
The range is a simple measure of variability, indicating the difference between the highest and...
116
The Soil Ecosystem
19.5K
Plants obtain inorganic minerals and water from the soil, which acts as a natural medium for land plants. The composition and quality of soil depend not only on the chemical constituents but also on the presence of living organisms. In general, soils contain three major components:
19.5K
Multiple Regression
2.9K
Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
2.9K


