相关实验视频
Updated: Sep 10, 2025

Watershed Planning within a Quantitative Scenario Analysis Framework
Published on: July 24, 2016
使用堆叠集团回归和基于SHAP的可解释的人工智能预测水质指数
Rakesh Choudhary1, Ajay Kumar2, Priyadharsini C3
1Department of Civil Engineering, National Institute of Technology Delhi, New Delhi, 110036, India. environmentrakesh@gmail.com.
这项研究引入了一种新的堆叠组合模型,用于预测水质指数 (WQI),达到高准确度. 可解释性人工智能 (XAI) 确定了关键的水质参数,提高了水资源管理和公共卫生.
科学领域:
- 环境科学
- 数据科学
- 水资源管理
背景情况:
- 准确的水质指数 (WQI) 预测对于有效的水资源管理和公共卫生保护至关重要.
- 现有的预测方法往往缺乏可解释性和高预测准确性.
- 物理化学参数是河水质量的关键指标.
研究的目的:
- 开发和验证用于WQI预测的新型堆叠回归组合模型.
- 整合可解释的人工智能 (XAI) 以实现模型的可解释性.
- 确定WQI预测中最有影响力的物理化学参数.
主要方法:
- 使用六种机器学习算法 (XGBoost,CatBoost,随机森林,梯度提升,额外树木,AdaBoost) 开发了一个堆叠的集合模型,并将线性回归作为元学习器.
- 该模型使用7个规范化物理化学参数对1987个印度河水质量样本 (2005-2014) 进行了训练.
- SHAP (沙普利添加剂解释) 用于模型解释性和特征重要性分析.
主要成果:
- 堆叠组合模型的R2为0.9952,调整后R2为0.9947,MAE为0.7637和RMSE为1.0704.
- 单个模型 CatBoost 和 Gradient Boosting 显示出强大的独立性能.
- SHAP分析确定溶解氧 (DO),生化氧需求 (BOD),导电率和pH为WQI预测最有影响力的参数.
结论:
- 与XAI一起提出的堆叠组合模型为WQI预测提供了高的预测准确性和可解释性.
- 这种方法增强了实时环境监测,并支持自动化政策框架.
- 通过更好的预测和透明度,这些发现为利益相关者建立了对水资源可持续性的信心.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
12:26Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
Published on: October 11, 2016
相关概念视频
Multiple Regression
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...
Steps in Outbreak Investigation
Testing Water Quality
Quality of Water
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Predicting Reaction Outcomes