为提升我国北方农牧交错带农业水资源利用效率,研究旨在提出一种基于机器学习极限梯度提升(eXtreme Gradient Boosting,XGBoost)算法的农业水资源利用效率评价和分析框架。首先,利用熵权TOPSIS(Technique for Order Preference by Simil...为提升我国北方农牧交错带农业水资源利用效率,研究旨在提出一种基于机器学习极限梯度提升(eXtreme Gradient Boosting,XGBoost)算法的农业水资源利用效率评价和分析框架。首先,利用熵权TOPSIS(Technique for Order Preference by Similarity to Ideal Solution)模型对北方农牧交错带七省区2008年至2021年的农业水资源利用效率进行测度;其次,将效率值作为XGBoost回归预测算法的先验样本进行训练测试,并使用贝叶斯优化(Bayesian Optimization,BO)算法对极限梯度提升回归预测模型的超参数进行优化。此外,应用五折交叉验证对TOPSIS-XGBoost回归模型结果进行稳健性检验;最后采用SHAP(Shapley Additive Explanation)模型系统分析影响北方农牧交错带七省区农业水资源利用效率的关键驱动因素。研究结果表明:2008年至2021年的北方农牧交错带七省区农业水资源利用效率整体有所提高,平均效率值由2008年的0.328上升至2021年的0.437,但总体效率均值较低;2021年河北省、宁夏回族自治区、辽宁省、陕西省和内蒙古自治区的农业水资源利用效率相对较高,效率值分布在0.40至0.59之间;甘肃省和山西省的农业水资源综合利用效率较低,效率值分别为0.33和0.31;BO-XGBoost回归预测模型测试集的R2较基准XGBoost模型提高了2.63%,且五折交叉验证的R2均值为0.96,表明模型误差较小,具有良好的预测性能和稳健性;供水模数、有效灌溉率以及农业规模化程度是影响七省区农业水资源利用效率的关键驱动因素。TOPSIS-BO-XGBoost-SHAP模型可为我国农业可持续发展提供科学参考和技术支持。展开更多
The behaviors of electrical resistivity vs temperature(ρ-T) of the molten p-type thermoelectric alloy Bi0.3Sb1.7Te3(at.%) were explored in heating and cooling processes. An obvious hump appeared on the ρ-T curve fro...The behaviors of electrical resistivity vs temperature(ρ-T) of the molten p-type thermoelectric alloy Bi0.3Sb1.7Te3(at.%) were explored in heating and cooling processes. An obvious hump appeared on the ρ-T curve from 932 ℃ to 1,020 ℃ at the heating process, while the curve became smooth in the following cooling, which suggests an irreversible temperature-induced liquid-liquid structure transition(TI-LLST) occurred in the liquid alloy. Based on this judgment, solidification experiments were carried out to find out the effects of the different liquid states. It was verified that, for the melt experiencing the presumed TI-LLST, both the nucleation and growth undercooling degrees were elevated and the solidification time was remarkably prolonged. On the other hand, the configuration of Bi0.3Sb1.7Te3 phase was refined, and its preferential orientation was weakened.展开更多
文摘为提升我国北方农牧交错带农业水资源利用效率,研究旨在提出一种基于机器学习极限梯度提升(eXtreme Gradient Boosting,XGBoost)算法的农业水资源利用效率评价和分析框架。首先,利用熵权TOPSIS(Technique for Order Preference by Similarity to Ideal Solution)模型对北方农牧交错带七省区2008年至2021年的农业水资源利用效率进行测度;其次,将效率值作为XGBoost回归预测算法的先验样本进行训练测试,并使用贝叶斯优化(Bayesian Optimization,BO)算法对极限梯度提升回归预测模型的超参数进行优化。此外,应用五折交叉验证对TOPSIS-XGBoost回归模型结果进行稳健性检验;最后采用SHAP(Shapley Additive Explanation)模型系统分析影响北方农牧交错带七省区农业水资源利用效率的关键驱动因素。研究结果表明:2008年至2021年的北方农牧交错带七省区农业水资源利用效率整体有所提高,平均效率值由2008年的0.328上升至2021年的0.437,但总体效率均值较低;2021年河北省、宁夏回族自治区、辽宁省、陕西省和内蒙古自治区的农业水资源利用效率相对较高,效率值分布在0.40至0.59之间;甘肃省和山西省的农业水资源综合利用效率较低,效率值分别为0.33和0.31;BO-XGBoost回归预测模型测试集的R2较基准XGBoost模型提高了2.63%,且五折交叉验证的R2均值为0.96,表明模型误差较小,具有良好的预测性能和稳健性;供水模数、有效灌溉率以及农业规模化程度是影响七省区农业水资源利用效率的关键驱动因素。TOPSIS-BO-XGBoost-SHAP模型可为我国农业可持续发展提供科学参考和技术支持。
基金financially supported by the National Natural Science Foundation of China(grant no.51371073)the Research Fund for the Doctoral Program of Higher Education of China(20110111110014)the National Basic Research Program of China(grant no.2012CB825702)
文摘The behaviors of electrical resistivity vs temperature(ρ-T) of the molten p-type thermoelectric alloy Bi0.3Sb1.7Te3(at.%) were explored in heating and cooling processes. An obvious hump appeared on the ρ-T curve from 932 ℃ to 1,020 ℃ at the heating process, while the curve became smooth in the following cooling, which suggests an irreversible temperature-induced liquid-liquid structure transition(TI-LLST) occurred in the liquid alloy. Based on this judgment, solidification experiments were carried out to find out the effects of the different liquid states. It was verified that, for the melt experiencing the presumed TI-LLST, both the nucleation and growth undercooling degrees were elevated and the solidification time was remarkably prolonged. On the other hand, the configuration of Bi0.3Sb1.7Te3 phase was refined, and its preferential orientation was weakened.
