pH is one of the significant properties of soil,and is closely related to the decomposition of soil organic matter,anion-cation balance,growth of plants and many other soil processes.In the present work,laser-induced ...pH is one of the significant properties of soil,and is closely related to the decomposition of soil organic matter,anion-cation balance,growth of plants and many other soil processes.In the present work,laser-induced breakdown spectroscopy(LIBS) technique coupled with random forest(RF) was proposed to quantify the pH of soil.First,LIBS spectra of soil was collected,and some common elements in soil were identified based on the National Institute of Science and Technology database.Then,in order to obtain a better predictive result,the influence of different input variables(full spectrum,different spectral ranges,the intensity of characteristic bands and characteristic lines) on the predictive performance of RF calibration model was explored with the evaluation indicators of root mean square error(RMSE) and coefficient of determination(R2),the characteristic bands of four elements(AI,Ca,Mg and Si) were determined as the optimal input variables.Finally,the predictive performance of RF calibration model was compared with partial least squares calibration model with the optimal input variables and model parameters,and RF calibration model showed a better predictive performance,and the four evaluation indicators of R_p^2,RMSEP,mean absolute error and mean relative error were 0.9687,0.1285,0.1114 and 0.0136,respectively.It indicates that LIBS technique coupled with RF algorithm is an effective method for pH determination of soil.展开更多
土壤pH是土壤的基本属性之一,对土壤环境管理有重要作用。以安徽省为研究区域,选用气候、地形、生物等17个相关环境变量,利用XGBoost和随机森林(random forest,RF)模型建立安徽省土壤pH空间预测模型,对比两模型的预测精度,并估算了两种...土壤pH是土壤的基本属性之一,对土壤环境管理有重要作用。以安徽省为研究区域,选用气候、地形、生物等17个相关环境变量,利用XGBoost和随机森林(random forest,RF)模型建立安徽省土壤pH空间预测模型,对比两模型的预测精度,并估算了两种制图结果的不确定性。结果表明:与随机森林模型相比,XGBoost模型对安徽省土壤pH的预测精度更高。XGBoost模型中eta、max_depth和nrounds对于模型的精度均具有一定的影响,eta的变化对于XGBoost模型精度影响最大。年均降水量(mean annual precipitation,MAP)、纬度(latitude,记为Y)、多尺度谷底平坦度(multiresolution index of valley bottom flatness,MRVBF)、年均温(mean annual temperature,MAT)、多尺度脊顶平坦度(multiresolution index of the ridge top flatness,MRRTF)、增强植被指数(enhanced vegetation index,EVI)对土壤pH建模有较大的影响,在两种模型的变量重要性排序中均重要。空间制图结果表明:两模型的预测结果大体趋势相同,安徽省土壤pH呈“南酸北碱”的趋势,但两者在部分地区的结果仍有区别。展开更多
The dynamics of forest ecology was studied. The pH values, electrical conductivities and concentrations of metal and nonmetal elements in rainfall, stream, through fall and stream flow were investigated based on the d...The dynamics of forest ecology was studied. The pH values, electrical conductivities and concentrations of metal and nonmetal elements in rainfall, stream, through fall and stream flow were investigated based on the data collected from a small mixed forest watershed of Pinus densifora sieb et Zucc, Pinus thunbergii Parh and Chamaecypari sobtusa sieb et Zucc ex Endl at Kiryu nature reserve and a small barren watershed at Jakujo nature reserve, Ootsu, Shiga, Japan. The results show that both the mixed forest ecosystems of pine and cypress and the soil draw from granite affect the pH values and metal elements of rainfall. And the contribution of the mixed forest is greater than that of the barren. Moreover, the amount of input of most elements is larger than that of output in the ecosystem, which shows the elemental accumulation in the related forest ecosystem.展开更多
Long-term changes in soil pH, the current status of soil acidification, and the response of bulk soil and soil water pH to experimental nitrogen addition under three subtropical forests were investigated in Dinghushan...Long-term changes in soil pH, the current status of soil acidification, and the response of bulk soil and soil water pH to experimental nitrogen addition under three subtropical forests were investigated in Dinghushan Biosphere Reserve of subtropical China. The results showed that the mineral soil pH at 0-20 cm depth declined significantly from 4.60-4.75 in 1980s to 3.84-4.02 in 2005. Nitrogen addition resulted in the decrease of pH in both bulk soil and soil water collected at 20-cm depth. The rapid decline of soil pH was attributed to long-term high atmospheric acid deposition (nitrogen and sulphur) therein. The forest at earlier succession stage with originally higher soil pH appeared to be more vulnerable to acid deposition than that at later succession stage with originally low soil pH.展开更多
基金support of National Natural Science Foundation of China(Nos.21873076,21675123,21605123,21375105)Natural Science Basic Research Plan in Shaanxi Province of China(No.2018JQ2013)Scientific Research Plan Projects of Shaanxi Education Department(No.17JK0780)。
文摘pH is one of the significant properties of soil,and is closely related to the decomposition of soil organic matter,anion-cation balance,growth of plants and many other soil processes.In the present work,laser-induced breakdown spectroscopy(LIBS) technique coupled with random forest(RF) was proposed to quantify the pH of soil.First,LIBS spectra of soil was collected,and some common elements in soil were identified based on the National Institute of Science and Technology database.Then,in order to obtain a better predictive result,the influence of different input variables(full spectrum,different spectral ranges,the intensity of characteristic bands and characteristic lines) on the predictive performance of RF calibration model was explored with the evaluation indicators of root mean square error(RMSE) and coefficient of determination(R2),the characteristic bands of four elements(AI,Ca,Mg and Si) were determined as the optimal input variables.Finally,the predictive performance of RF calibration model was compared with partial least squares calibration model with the optimal input variables and model parameters,and RF calibration model showed a better predictive performance,and the four evaluation indicators of R_p^2,RMSEP,mean absolute error and mean relative error were 0.9687,0.1285,0.1114 and 0.0136,respectively.It indicates that LIBS technique coupled with RF algorithm is an effective method for pH determination of soil.
文摘土壤pH是土壤的基本属性之一,对土壤环境管理有重要作用。以安徽省为研究区域,选用气候、地形、生物等17个相关环境变量,利用XGBoost和随机森林(random forest,RF)模型建立安徽省土壤pH空间预测模型,对比两模型的预测精度,并估算了两种制图结果的不确定性。结果表明:与随机森林模型相比,XGBoost模型对安徽省土壤pH的预测精度更高。XGBoost模型中eta、max_depth和nrounds对于模型的精度均具有一定的影响,eta的变化对于XGBoost模型精度影响最大。年均降水量(mean annual precipitation,MAP)、纬度(latitude,记为Y)、多尺度谷底平坦度(multiresolution index of valley bottom flatness,MRVBF)、年均温(mean annual temperature,MAT)、多尺度脊顶平坦度(multiresolution index of the ridge top flatness,MRRTF)、增强植被指数(enhanced vegetation index,EVI)对土壤pH建模有较大的影响,在两种模型的变量重要性排序中均重要。空间制图结果表明:两模型的预测结果大体趋势相同,安徽省土壤pH呈“南酸北碱”的趋势,但两者在部分地区的结果仍有区别。
文摘The dynamics of forest ecology was studied. The pH values, electrical conductivities and concentrations of metal and nonmetal elements in rainfall, stream, through fall and stream flow were investigated based on the data collected from a small mixed forest watershed of Pinus densifora sieb et Zucc, Pinus thunbergii Parh and Chamaecypari sobtusa sieb et Zucc ex Endl at Kiryu nature reserve and a small barren watershed at Jakujo nature reserve, Ootsu, Shiga, Japan. The results show that both the mixed forest ecosystems of pine and cypress and the soil draw from granite affect the pH values and metal elements of rainfall. And the contribution of the mixed forest is greater than that of the barren. Moreover, the amount of input of most elements is larger than that of output in the ecosystem, which shows the elemental accumulation in the related forest ecosystem.
基金Supported by the National Natural Science Foundation of China (Nos.30270282 and 40703030)the Key Project of the Chinese Ministry of Education (No.704037)+1 种基金the Doctoral Scientific Research Foundation of Guilin University of Electronic Technology,China (No.Z20718)the Guangxi Provincial Department of Education,China (No.200707MS048)
文摘Long-term changes in soil pH, the current status of soil acidification, and the response of bulk soil and soil water pH to experimental nitrogen addition under three subtropical forests were investigated in Dinghushan Biosphere Reserve of subtropical China. The results showed that the mineral soil pH at 0-20 cm depth declined significantly from 4.60-4.75 in 1980s to 3.84-4.02 in 2005. Nitrogen addition resulted in the decrease of pH in both bulk soil and soil water collected at 20-cm depth. The rapid decline of soil pH was attributed to long-term high atmospheric acid deposition (nitrogen and sulphur) therein. The forest at earlier succession stage with originally higher soil pH appeared to be more vulnerable to acid deposition than that at later succession stage with originally low soil pH.
