基于NDVI与偏最小二乘回归的荒漠化地区植被覆盖度高光谱遥感估测

以星载高光谱影像Hyperion为数据源,系统比较了NDVI与偏最小二乘回归（PLS）估测荒漠化地区植被覆盖度的能力,模型的建立（n=46）与独立检验所用样本（n=10）均为地面实测数据。研究结果表明,基于星载高光谱数据的NDVI与PLS模型可以有效地估测荒漠化地区植被覆盖度。相比于宽波段NDVI（RMSEP=10.5618）及基于803.3/671.02 nm计算的标准高光谱NDVI（RMSEP=8.3863）,选择特定高光谱波段（823.65/701.55 nm）构建的NDVI预测植被覆盖度的误差明显较低（RMSEP=6.5189）。基于高光谱所有波段原始反射率、一阶导数及包络线去除光谱的PLS回归模型表现,要明显优于仅利用两个波段信息的NDVI,其中基于原始反射率的PLS回归模型表现最佳,RMSEP为4.4998,约为因变量平均值的23%。     

基于纹理特征与LSSVM的青土湖地物提取

纹理特征作为一种非光谱信息能够增强地物之间的特征差异,这对于高分辨率遥感影像的地物提取有着重要意义。以青土湖为研究区,以Worldview-2影像为数据源,通过引入权重因子定义联合概率函数来确定最佳窗口尺度,利用灰度共生矩阵提取最佳窗口尺度下的纹理特征,将其与原始遥感影像合成,采用最小二乘支持向量机（LSSVM）进行地物提取,将提取结果与仅利用光谱信息的支持向量机（SVM）提取结果、辅以纹理特征的SVM提取结果对比分析。结果表明：此方法可以更加快速准确地提取青土湖地物,精度高达85.86%,优于仅利用光谱信息的SVM的65.13%,辅以纹理特征的SVM的73.45%,可为地物破碎的干旱区高分辨率遥感影像地物提取提供有益借鉴。     

A Novel Multiple-Kernel Support Vector Regression Algorithm for Estimation of Water Quality Parameters

Natural Resources Research - The quality of surface waters plays a key role in the sustainability of ecological systems. Measuring water quality parameters (WQPs) is of high...     

Prediction of Vibration Velocity Generated in Mine Blasting Using Support Vector Regression Improved by Optimization Algorithms

Natural Resources Research - Ground vibration generated from blasting is a detrimental side effect of the use of explosives to break the rock mass in mines. Therefore, accurately predicting ground...     

Estimation of Ground Vibration Intensity Induced by Mine Blasting using a State-of-the-Art Hybrid Autoencoder Neural Network and Support Vector Regression Model

Natural Resources Research - In surface mining, blasting is an indispensable method for fragmenting rock masses. Nevertheless, it can inherently induce many side effects like ground vibrations. At...     

Prediction of Blast-Induced Rock Movement During Bench Blasting: Use of Gray Wolf Optimizer and Support Vector Regression

Natural Resources Research - A large ore loss and dilution can be expected when using a pre-blast ore boundary for shovel guidance because of the movement and re-distribution of ore in the muck...     

Economic-Geological Estimation of Gold and Ore Deposits Using Information-Analytical System for the Selection of Analogues

The computer system is developed for evaluation of gold deposits over the world using data collected by experts in the field of gold deposit geology. With the system in use, gold object of interest can be described on the basis of selected groups of tags. The similarity of the considered object to an object from the database is estimated by designed algorithms on the basis of available information characterizing the considered object. These algorithms allow to apply mathematical methods for analysis of the problem what improves quality and reliability of the results. By the method of analogue determination, user can always evaluate unknown properties of the considered object, as for example, ore formation type, economic geological estimate of the deposit on the basis of known properties of the determined analogue.The software equipped by an intuitive graphical interface is developed with use of GIS technologies and modern methods of object-oriented programming.     

Empirical Methods for Detecting Regional Trends and Other Spatial Expressions in Antrim Shale Gas Productivity, with Implications for Improving Resource Projections Using Local Nonparametric Estimation Techniques

The primary objectives of this research were to (1) investigate empirical methods for establishing regional trends in unconventional gas resources as exhibited by historical production data and (2) determine whether or not incorporating additional knowledge of a regional trend in a suite of previously established local nonparametric resource prediction algorithms influences assessment results. Three different trend detection methods were applied to publicly available production data (well EUR aggregated to 80-acre cells) from the Devonian Antrim Shale gas play in the Michigan Basin. This effort led to the identification of a southeast–northwest trend in cell EUR values across the play that, in a very general sense, conforms to the primary fracture and structural orientations of the province. However, including this trend in the resource prediction algorithms did not lead to improved results. Further analysis indicated the existence of clustering among cell EUR values that likely dampens the contribution of the regional trend. The reason for the clustering, a somewhat unexpected result, is not completely understood, although the geological literature provides some possible explanations. With appropriate data, a better understanding of this clustering phenomenon may lead to important information about the factors and their interactions that control Antrim Shale gas production, which may, in turn, help establish a more general protocol for better estimating resources in this and other shale gas plays.