[目的]对区域性泥石流敏感性进行分析,为吉林省洮南市泥石流灾害预测研究提出一种高效快捷的分析模型。[方法]针对现行大多数概率统计模型预测率较低的不足,利用人工智能算法中效果明显的随机森林算法,以吉林省洮南市西北部山区为研究区...[目的]对区域性泥石流敏感性进行分析,为吉林省洮南市泥石流灾害预测研究提出一种高效快捷的分析模型。[方法]针对现行大多数概率统计模型预测率较低的不足,利用人工智能算法中效果明显的随机森林算法,以吉林省洮南市西北部山区为研究区域,选用高程、坡度、坡向、平面曲率、剖面曲率、河流、归一化差分植被指数、地形湿度指数、土地利用及岩性10个评价因子构建了频率比和随机森林泥石流敏感性评价模型进行对比验证。模型准确性的验证方法采用受试者特征曲线(ROC曲线)及累积频率曲线下面积(area under curve,AUC)。[结果]随机森林对研究区泥石流敏感性进行分析,并通过GIS将敏感性图分为5个敏感性区域,位于高敏感性区以上的灾害点占82.3%。验证模型成功率及预测率分别为88.4%与90.4%,相较于频率比的成功率及预测率(86.4%和75.1%)效果良好。[结论]在洮南市北部进行泥石流敏感性分析中,采用随机森林方法进行建模,并利用频率比方法进行对比,结果显示随机森林法结果可靠准确。展开更多
CdSxSe1-x quantum dots were fabricated by a simple spin-coating heat volatilization method on InP wafer.Temperature dependent photoluminescence of CdSxSe1-x quantum dots was carried out in a range of 10-300 K.The inte...CdSxSe1-x quantum dots were fabricated by a simple spin-coating heat volatilization method on InP wafer.Temperature dependent photoluminescence of CdSxSe1-x quantum dots was carried out in a range of 10-300 K.The integrated photoluminescence intensity revealed an anomalous behavior with increasing temperature in the range of 180-200 K.The band gap energy showed a redshift of 61.34 meV when the temperature increased from 10 to 300 K.The component ratio of S to Se in the CdSxSe1-x quantum dots was valued by both the X-ray diffraction data and photoluminescence peak energy at room temperature according to Vegard Law.Moreover,the parameters of the Varshni relation for CdS0.9Se0.1 materials were also obtained using photoluminescence peak energy as a function of temperature and the best-fit curve:α=(3.5 ± 0.1)10-4 eV/K,and β=210 ± 10 K (close to the Debye temperature θD of the material).展开更多
文摘[目的]对区域性泥石流敏感性进行分析,为吉林省洮南市泥石流灾害预测研究提出一种高效快捷的分析模型。[方法]针对现行大多数概率统计模型预测率较低的不足,利用人工智能算法中效果明显的随机森林算法,以吉林省洮南市西北部山区为研究区域,选用高程、坡度、坡向、平面曲率、剖面曲率、河流、归一化差分植被指数、地形湿度指数、土地利用及岩性10个评价因子构建了频率比和随机森林泥石流敏感性评价模型进行对比验证。模型准确性的验证方法采用受试者特征曲线(ROC曲线)及累积频率曲线下面积(area under curve,AUC)。[结果]随机森林对研究区泥石流敏感性进行分析,并通过GIS将敏感性图分为5个敏感性区域,位于高敏感性区以上的灾害点占82.3%。验证模型成功率及预测率分别为88.4%与90.4%,相较于频率比的成功率及预测率(86.4%和75.1%)效果良好。[结论]在洮南市北部进行泥石流敏感性分析中,采用随机森林方法进行建模,并利用频率比方法进行对比,结果显示随机森林法结果可靠准确。
基金supported by the NSFC (No. 50532080)the Key Laboratory Projects of The Education Department of Liaoning Province (No. 20060131)
文摘CdSxSe1-x quantum dots were fabricated by a simple spin-coating heat volatilization method on InP wafer.Temperature dependent photoluminescence of CdSxSe1-x quantum dots was carried out in a range of 10-300 K.The integrated photoluminescence intensity revealed an anomalous behavior with increasing temperature in the range of 180-200 K.The band gap energy showed a redshift of 61.34 meV when the temperature increased from 10 to 300 K.The component ratio of S to Se in the CdSxSe1-x quantum dots was valued by both the X-ray diffraction data and photoluminescence peak energy at room temperature according to Vegard Law.Moreover,the parameters of the Varshni relation for CdS0.9Se0.1 materials were also obtained using photoluminescence peak energy as a function of temperature and the best-fit curve:α=(3.5 ± 0.1)10-4 eV/K,and β=210 ± 10 K (close to the Debye temperature θD of the material).
