Generating soil thickness maps by means of geomorphological-empirical approach and random forest algorithm in Wanzhou County,Three Gorges Reservoir     

《地学前缘(英文版)》2023,14(2):101514

Soil thickness, intended as depth to bedrock, is a key input parameter for many environmental models. Nevertheless, it is often difficult to obtain a reliable spatially exhaustive soil thickness map in wide-area applications, and existing prediction models have been extensively applied only to test sites with shallow soil depths. This study addresses this limitation by showing the results of an application to a section of Wanzhou County (Three Gorges Reservoir Area, China), where soil thickness varies from 0 to ～40 m. Two different approaches were used to derive soil thickness maps: a modified version of the geomorphologically indexed soil thickness (GIST) model, purposely customized to better account for the peculiar setting of the test site, and a regression performed with a machine learning algorithm, i.e., the random forest, combined with the geomorphological parameters of GIST (GIST-RF). Additionally, the errors of the two models were quantified, and validation with geophysical data was carried out. The results showed that the GIST model could not fully contend with the high spatial variability of soil thickness in the study area: the mean absolute error was 10.68 m with the root-mean-square error (RMSE) of 12.61 m, and the frequency distribution residuals showed a tendency toward underestimation. In contrast, GIST-RF returned a better performance with the mean absolute error of 3.52 m and RMSE of 4.56 m. The derived soil thickness map could be considered a critical fundamental input parameter for further analyses.  相似文献   

基于机器学习模型的淮河流域中长期径流预报研究     

胡义明  陈腾  罗序义  唐超  梁忠民 《地学前缘》2022,29(3):284-291

准确可靠的中长期径流预报是支撑水资源科学调配、提高水资源利用效率的关键。本研究采用AdaBoost模型(AdB)、随机森林模型(RF)和支持向量机模型(SVM)进行淮河流域王家坝和蚌埠站当年11月至次年10月共12个月的中长期径流预报研究。采用置换准确度重要性度量法从130项气象-气候因子及前期降雨/流量构建的1 562个因子变量中筛选出影响各月径流的关键因子,构建了基于AdB、RF和SVM模型的各月径流预报模型,模型参数采用随机搜索技术并结合交叉验证方式确定。采用变幅误差合格率和等级(五级)预报合格率指标对模型的预报精度进行了评估。变幅误差合格率指标表明,王家坝12个月的平均合格率分别为99.8%(AdB)、96.6%(RF)和95.9%(SVM),蚌埠站分别为100%(AdB)、94.8%(RF)和93.8%(SVM);等级预报合格率指标表明,王家坝12个月的平均合格率分别为79.0%(AdB)、76.4%(RF)和79.9%(SVM),蚌埠站分别为81.0%(AdB)、75.6%(RF)和76.6%(SVM)。模型均具有较好的预报效果,但RF和SVM模型对于高流量值的预报存在偏低现象,AdB模型整体上优于RF和SVM模型。  相似文献   

基于机器学习的表层土壤成矿元素空间预测: 以稀有金属铷元素为例     

戴亮亮  聂小力  郭军  巩浩  吴欢欢  张涛  汤媛媛  毛聪  彭志刚  贺灿 《现代地质》2022,36(3):972-978

近些年随着土地质量地球化学调查工作的开展,获取了大量表层土壤样品数据。然而,这些数据也存在一个明显的缺陷,即1∶50 000大比例尺表层土壤数据往往缺少成矿元素。鉴于土壤成矿元素含量对于矿产资源勘查的重要指示作用,尝试基于现有数据对大比例尺表层土壤成矿元素含量提供一个补全方案。以稀有金属铷元素为例,采用随机森林算法把同一区域2 548组1∶250 000小比例尺表层土壤数据按照8∶2的比例随机分为两组,用80%的数据进行训练建模,20%的数据对模型进行验证。采用变量重要性度量排序和构建学习曲线的组合方法优选了8种元素(K、B、Ni、V、Zn、As、Co、Cu)作为预测变量,模型对训练数据和测试数据的拟合优度R²分别达到0.983 2和0.895 6,说明预测变量的优选方法是有效的。随后将1∶50 000表层土壤的上述预测变量数据作为输入变量导入模型中,得到预测的Rb元素含量,预测结果比较符合实际特征。本研究表明将大数据机器学习随机森林算法引入表层土壤地球化学元素含量空间定量预测具有可行性,可进一步拓展土地质量地球化学数据的服务应用维度。  相似文献   

帽峰山地区典型小流域主要森林类型土壤渗透性     

刘千红  彭益军  张剑  罗定贵 《地下水》2015,(1):9-11

采集帽峰山地区典型小流域主要林地类型(青冈林、毛竹林、凤尾竹林、桉树林)原状土样进行土壤剖面(0~20 cm、20~40 cm、40~60 cm)渗透系数及其相关因子的实验研究,结果表明:各种林地类型土壤渗透系数在剖面上均表现出从上到下递减的特点,毛竹、青冈、凤尾竹、桉树林的土壤剖面渗透系数变化范围分别为13.64~4.91、10.49~3.63、8.16~2.96、7.92~3.71 m/d。由于20~40 cm、40~60 cm土层渗透系数差异性相对较小,土壤渗透性剖面可简化为上、下两个亚层,上部亚层渗透系数是下部亚层的1.89~2.42倍。各种林地类型土壤渗透系数与孔隙度、根密度呈正相关,与干容重呈负相关,与根径关系相关性方向具有不确定性。不同林地类型土壤渗透系数与干容重、根密度、根径之间的相关程度存在较大差异,但均表现出与孔隙度之间存在良好相关性。  相似文献   

基于时间序列统计特性的森林变化监测   总被引：1，自引：0，他引：1  

黄春波  佃袁勇  周志翔  王娣  陈瑞冬 《遥感学报》2015,19(4):657-668

森林动态变化分析对揭示生态系统环境变化及植被恢复和布局重建等具有重要意义,时间序列的遥感数据为森林监测提供了基础数据。本文根据森林植被的统计学特性,在暗目标法的基础上,利用归一化植被指数NDVI实现森林样本自动选择;并融合NDVI构建了新的综合森林特征指数(Integrated Forest Z-Score,IFZ);以时间序列的IFZ分析森林动态信息,实现森林变化动态监测。以三峡大坝及周边区域森林为研究区,利用2001年至2012年每年生长季节(5月—10月)的Landsat TM影像检验本文算法。基于2002年、2006年和2010年三期7月—9月的Quick Bird影像的精度分析结果发现:研究区森林变化检测的总体精度可达96.53%,Kappa系数为0.9512。在添加NDVI指数后构建的IFZ提高了总体监测精度。其中,毁林类别的检测精度提高显著,漏检率和误检率分别为2.74%和3.64%;干扰后重建的森林类别的检测精度有一定提高,其漏检率和误检率分别为10.79%和10.51%。研究结果表明,改进暗目标法能提高森林样本的选样效率,添加NDVI的IFZ能提高森林动态变化的识别度。此外,本算法不仅能定性识别森林变化,而且能定量提供森林干扰发生时间和干扰强度。  相似文献   

Carbon stock of oil palm plantations and tropical forests in Malaysia: A review          下载免费PDF全文

Lip Khoon Kho  Martin Rudbeck Jepsen 《Singapore journal of tropical geography》2015,36(2):249-266

In Malaysia, the main land change process is the establishment of oil palm plantations on logged‐over forests and areas used for shifting cultivation, which is the traditional farming system. While standing carbon stocks of old‐growth forest have been the focus of many studies, this is less the case for Malaysian fallow systems and oil palm plantations. Here, we collate and analyse Malaysian datasets on total carbon stocks for both above‐ and below‐ground biomass. We review the current knowledge on standing carbon stocks of 1) different forest ecosystems, 2) areas subject to shifting cultivation (fallow forests) and 3) oil palm plantations. The forest ecosystems are classified by successional stage and edaphic conditions and represent samples along a forest succession continuum spanning pioneer species in shifting cultivation fallows to climax vegetation in old‐growth forests. Total carbon stocks in tropical forests range from 4 to 384 Mg C/ha, significantly wider than the range of total carbon stocks of oil palm plantations, 2 to 60 Mg C/ha. Conversion of old‐growth forest areas to oil palm plantations leads to substantial reduction in carbon storage, while conversion of forest fallows to oil palm plantations may sustain or even increase the standing carbon stock.  相似文献   

Assessing the utility WorldView-2 imagery for tree species mapping in South African subtropical humid forest and the conservation implications: Dukuduku forest patch as case study     

《International Journal of Applied Earth Observation and Geoinformation》2015

Indigenous forest biome in South Africa is highly fragmented into patches of various sizes (most patches < 1 km²). The utilization of timber and non-timber resources by poor rural communities living around protected forest patches produce subtle changes in the forest canopy which can be hardly detected on a timely manner using traditional field surveys. The aims of this study were to assess: (i) the utility of very high resolution (VHR) remote sensing imagery (WorldView-2, 0.5–2 m spatial resolution) for mapping tree species and canopy gaps in one of the protected subtropical coastal forests in South Africa (the Dukuduku forest patch (ca.3200 ha) located in the province of KwaZulu-Natal) and (ii) the implications of the map products to forest conservation. Three dominant canopy tree species namely, Albizia adianthifolia, Strychnos spp. and Acacia spp., and canopy gap types including bushes (grass/shrubby), bare soil and burnt patches were accurately mapped (overall accuracy = 89.3 ± 2.1%) using WorldView-2 image and support vector machine classifier. The maps revealed subtle forest disturbances such as bush encroachment and edge effects resulting from forest fragmentation by roads and a power-line. In two stakeholders’ workshops organised to assess the implications of the map products to conservation, participants generally agreed amongst others implications that the VHR maps provide valuable information that could be used for implementing and monitoring the effects of rehabilitation measures. The use of VHR imagery is recommended for timely inventorying and monitoring of the small and fragile patches of subtropical forests in Southern Africa.  相似文献   

随机森林机器算法在江苏省小麦赤霉病病穗率预测中的应用   总被引：1，自引：0，他引：1  

徐敏  徐经纬  谢志清  高苹  李亚春  缪璟秋 《气象学报》2020,78(1):143-153

基于2002—2018年江苏省13个市的小麦赤霉病病穗率资料与生育期观测资料、相应时段内的逐日气象数据,应用随机森林机器学习算法,分生育期、分区域定量评估影响病穗率的主要气象因子特征变量和贡献率,按不同起报时间建立预测模型并进行验证。结果表明,各生育期重要特征变量贡献率的排序为:抽穗扬花期＞拔节期＞越冬期。抽穗扬花期湿度、连续≥3 d的雨日和日照对赤霉病起主导作用,拔节期日照、降雨量、湿度和雨日与越冬期气温和降雪对赤霉病均具有前期影响,甄别出的重要特征变量排序结果符合赤霉病菌发育、释放、侵染和流行规律;基于随机森林算法建立的病穗率预测模型的精度与重要特征变量个数、赤霉病发生区域、M_try参数设定、生育期有关;最早可在3月初进行预测,预测时效近3个月,起报时间越接近乳熟期,输入的重要特征变量越多,则病穗率预测准确率越高,病穗率模拟值与实测值的波动趋势完全一致,对赤霉病“中等”和“偏重”等级模拟效果好,表明随机森林算法在赤霉病预测中有较高的可靠性和业务应用潜力。   相似文献   

合成孔径雷达森林资源监测技术研究综述     

李增元  赵磊  李堃  陈尔学  万祥星  徐昆鹏 《南京气象学院学报》2020,12(2):150-158

合成孔径雷达（Synthetic Aperture Radar,SAR）技术凭借其全天时、全天候的成像能力以及对森林垂直结构信息敏感的特点,在森林资源监测中具有独特的优势,已成为当前森林资源遥感调查技术的研究热点.本文首先介绍了SAR森林资源监测技术的发展背景、发展轨迹和相关知识;然后,重点阐述了极化SAR、干涉SAR、极化干涉SAR和层析SAR在林地覆盖类型分类、变化检测以及森林参数定量化估测应用中的技术方法;最后,就SAR在森林资源监测研究和应用中存在的问题与发展趋势进行了总结与展望.  相似文献   

基于机器学习的降雨量雷达回波数据建模与预测     

陈晓平  陈易旺  施建华 《南京气象学院学报》2020,12(4):483-494

以浙江省2016年1-10月的雷达回波强度数据为基础,分别应用随机森林模型、BP神经网络模型、卷积神经网络模型来预测降雨量并进行对比.建模分析结果表明,随机森林模型预测效果精确度较低,容易低估较大的降雨强度,而BP神经网络和卷积神经网络预测的效果都比随机森林好,特别是卷积神经网络,其预测值与真实值更加接近,且对较大的降雨强度拟合较好.  相似文献