基于距离相关系数和KNN回归模型的森林蓄积量估测研究

【目的】探究Landsat8 OLI数据和KNN算法在森林蓄积量估测中的潜力。【方法】以湖南省湘潭县为研究区,采用Landsat8 OLI数据和同时期的二类调查数据,通过距离相关系数筛选特征,分别采用线性回归模型(MLR)、K-近邻模型(KNN)、距离加权KNN模型(DW-KNN)和优化欧式KNN模型(FW-KNN)对森林蓄积量进行估测。使用十折交叉方法进行精度检验,对检验结果进行对比分析。【结果】3种KNN模型的估测结果均高于传统的线性模型,并且在3种KNN模型中,FW-KNN算法效果最好,决定系数达到0.69,为3种模型中最高;3种KNN模型中,本研究优化欧氏距离KNN模型的估测精度最高,其均方根误差为30.3%,相比于传统KNN模型的均方根误差降低了5.1%,相比于DW-KNN模型降低了3.3%。【结论】采用DW-KNN蓄积量估测结果明显优于其他两种模型,说明通过特征与蓄积量的相关性优化样本间的距离是一种可行的KNN优化方法。     

基于Landsat和MODIS数据融合的农牧区NPP模拟

天山北坡是中国重要的农牧业发展基地,利用遥感数据准确获取植被净初级生产力(Net primary productivity,NPP)的时空信息,对于合理分配农牧业草地资源具有重要意义。由于受到天气影响及卫星传感器受到时间分辨率和空间分辨率的限制,获取既具有中空间分辨率、又具有高时间分辨率的遥感数据比较困难。本文基于中空间分辨率Landsat 8 OLI数据与高时间分辨率MODIS数据,采用遥感数据时空融合STARFM算法,获取中空间分辨率和高时间分辨率序列的遥感数据,以天山北坡中段区域为实验区,结合CASA模型,对区域内植被NPP进行模拟。结果表明,2016年内8个时期,融合后的NDVI数据与对应时刻的Landsat 8 OLI NDVI数据的相关系数不小于0.759,偏差在0.006 2～0.009 4之间,均方根误差在0.074～0.135之间;利用融合数据与CASA模型协同模拟的NPP具有良好的空间细节信息,NPP模拟值与野外实测值决定系数R~2为0.860 1,表明两者具有较好的相关性。本研究为多源遥感影像融合技术与光能利用率模型协同模拟NPP提供了新的思路。     

Developing the framework for a risk map for mite vectored viruses in wheat resulting from pre-harvest hail damage

There is a strong economic incentive to reduce mite-vectored virus outbreaks. Most outbreaks in the central High Plains of the United States occur in the presence of volunteer wheat that emerges before harvest as a result of hail storms. This study provides a conceptual framework for developing a risk map for wheat diseases caused by mite-vectored viruses based on pre-harvest hail events. Traditional methods that use NDVI were found to be unsuitable due to low chlorophyll content in wheat at harvest. Site-level hyperspectral reflectance from mechanically hailed wheat showed increased canopy albedo. Therefore, any increase in NIR combined with large increases in red reflectance near harvest can be used to assign some level of risk. The regional model presented in this study utilized Landsat TM/ETM+ data and MODIS imagery to help gap-fill missing data. NOAA hail maps that estimate hail size were used to refine the area most likely at risk. The date range for each year was shifted to account for annual variations in crop phenology based on USDA Agriculture statistics for percent harvest of wheat. Between 2003 and 2013, there was a moderate trend (R² = 0.72) between the county-level insurance claims for Cheyenne County, Nebraska and the area determined to be at risk by the model (excluding the NOAA hail size product due to limited availability) when years with low hail claims (<400 ha) were excluded. These results demonstrate the potential of an operational risk map for mite-vectored viruses due to pre-season hail events.     

Information extraction and dynamic evaluation of soil salinization with a remote sensing method in a typical county on the Huang-Huai-Hai Plain of China

Monitoring the dynamics of soil salinization is of great importance for agricultural production. This study selected Yucheng County, a typical county on the Huang-Huai-Hai Plain (HHHP) of China, as the study area and evaluated the spatial and temporal variation of soil salinization. Three methods, consisting of principal component analysis (PCA) transformation, tasseled cap (TC) transformation, and optimal band combination (OBC), were used to extract information from an early Landsat multispectral scanner (MSS) image from 1984, and their advantages were compared. In addition, OBC was used on a thematic mapper (TM) image from 2009. An iteratively self-organizing data analysis algorithm was used together with prior knowledge of likely classifications to interpret the MSS and TM images for data classification. Finally, a transfer matrix method was used to assess the spatial and temporal variability of soil salinization and analyze the driving factors of soil salinization. Compared to PCA transformation and OBC, TC transformation was a more effective method for extracting soil salinization information from the MSS sensor. The results indicate that a soil area of approximately 298 km² was affected by salinity in 1984 in Yucheng County, of which 5.40%, 11.96%, and 12.75% were classified as being subject to slight, moderate, and severe salinization, respectively. In 2009, the saline area was reduced to only 146 km², of which 10.70% and 3.75% were characterized by slight to moderate salinization and no severe salinization, respectively. The saline land decreased at an average rate of 6 km² per year. This decrease was probably a result of lower groundwater depth, increased organic fertilizer or crop straw in soil, changed land use type, and increased vegetation coverage.     

用遥感影像提取大别山区水稻种植面积——以Landsat 8为例

本研究选取安徽省安庆市大别山为研究区,包括太湖县、岳西县、宿松县和潜山县,选取2016年和2017年的6景Landsat 8卫星遥感影像,通过遥感影像提取水稻种植面积,分析大别山区的水稻种植面积分布,并对研究区域的水稻种植面积进行动态实时监测。用遥感解译方法分别提取了研究区内的晚稻种植面积,并利用随机点验证和Kappa系数验证结果精度。结果表明:2017年和2016年水稻种植面积的提取精度分别为93.44%、93.78%,Kappa系数分别为0.86、0.83,证明水稻提取效果精确;对比研究区域各个县内的2017年和2016年晚稻种植面积,发现安庆市大别山区太湖县、潜山县、岳西县的水稻种植面积变化率均在5%以内,属于正常变化,由于2016年宿松县遭遇了水灾,部分农田被淹没,故宿松县2017年水稻种植面积相比2016年增加了13.01%;对比传统的农作物种植面积统计方法,利用遥感的方法更省人力、物力、财力,并且能精确、快速地实现对农作物的实时动态监测。     

1990—2019年阿拉尔垦区植被覆盖时空变化特征分析

监测植被覆盖变化对区域生态环境评价和可持续发展具有重要意义。本文基于Landsat遥感影像和相关统计数据,运用像元二分模型和重心转移模型等方法分析阿拉尔垦区1990—2019年近30年的植被覆盖时空变化特征。结果表明：1990—2019年,阿拉尔垦区平均植被覆盖面积呈增加趋势,高和极高植被覆盖区的面积呈增加趋势,差异显著,分别增加了674 km²和1 147 km²;阿拉尔垦区植被覆盖变化存在时段性和区域性差异,时段上,2005—2010年垦区西北部开始出现植被,以中覆盖类型为主,区域上,垦区西北部植被覆盖的增加趋势最显著;近30年,垦区植被覆盖重心整体向东北方向转移;气候对阿拉尔垦区植被覆盖变化有一定的影响,但人类活动影响最直接。在未来发展中应注重保护自然植被,有计划地开垦土地,合理调整垦区农业结构,科学分配水权,保证垦区生态用水,实现可持续发展。     

基于Landsat数据的条件植被温度指数升尺度转换方法

以陕西省关中平原为研究区域,应用点扩散函数、混合像素面积权重法和中值像素变异权重法将基于Landsat卫星遥感数据反演的分辨率为30 m的条件植被温度指数(VTCI)干旱监测结果上推至930 m的干旱监测结果,并与Aqua MODIS数据反演的分辨率为930 m的VTCI干旱监测结果进行对比分析,以期为两种空间尺度的干旱监测结果的综合应用提供技术支持。以MODIS数据反演的VTCI为参考,应用相关系数、均方根误差、半变异函数的估计值和图像纹理特征等对尺度上推的VTCI进行评价。结果表明,点扩散函数和混合像素面积权重法的尺度上推效果均较好,而中值像素变异权重法的尺度上推效果较差,说明点扩散函数和混合像素面积权重法均适用于研究区域VTCI干旱监测结果的尺度转换,且点扩散函数的数据处理过程更为简单。典型样点VTCI的尺度上推结果表明,空间异质性越小,尺度上推的结果越好。     

Prediction of pine mistletoe infection using remote sensing imaging: A comparison of the artificial neural network model and logistic regression model

In this study, the prediction of pine mistletoe distribution in Scots pine ecosystems was explored using remote sensing variables to compare the multilayer perceptron (MLP) artificial neural network (ANN) and logistic regression (LR) model performances. For this purpose, 109 sample plots were distinguished in pure Scots pine forests (natural) in the Eastern Black Sea Region of Turkey. Distinguishing mistletoe-infected stands (69) and uninfected stands (40) was performed with field observations. The variables acquired from Landsat 8 (Level 1) images were used as independent variables for independent-sample t-test, MLP ANN and LR models. Remote sensing variables indicated that mistletoe-infected stands were in drier areas with a lower vegetation-leaf area index. Based on the performance results of both models, the sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV) and accuracy of the MLP ANN model were superior to those of the LR model. The prediction percentages (SEN, SPE, PPV and NPV) of mistletoe-infected stands were better than the prediction percentages of uninfected stands. The prediction accuracies of LR and MLP ANN models were 74.3% and 89.6%, respectively. However, all remote sensing variables were included in the prediction equation of the MLP ANN model, while the thermal infrared 1 (TIRS1) variable was included in the LR model. In the MLP ANN model, the TIRS1 variable also had the highest normalized importance (100%). The area under the curve (AUC) value for identifying the mistletoe-infected stands of Scots pine forests used by the MLP ANN model (0.892 ± 0.034) was higher than in the LR model (0.838 ± 0.039), explaining the more accurate predictions obtained from the MLP ANN model. The MLP ANN model showed much better performance than the LR model. The results of this study are expected to make important contributions to the identification of potential mistletoe-infected areas.     

Applying Local Measures of Spatial Heterogeneity to Landsat-TM Images for Predicting Wildfire Occurrence in Mediterranean Landscapes

In mountainous Mediterranean regions, land abandonment processes in past decades are hypothesized to trigger secondary vegetal succession and homogenization, which in recent years has increased the size of burned areas. We conducted an analysis of temporal changes in landscape vegetal spatial pattern over a 15-year period (1984–1998) in a rural area of 672.3 km² in Eastern Spain to investigate the relationship between local landscape heterogeneity and wildfire occurrence. Heterogeneity was analyzed from textural metrics derived from non-classified remote sensing data at several periods, and was related to wildfire history in the study area. Several neural network models found significant relationships between local spatial pattern and future fire occurrence. In this study, sensitivity analysis of the texture variables suggested that fire occurrence, estimated as probability of burning in the near future, increased where local homogeneity was higher.     

Evaluating Modified Atmospheric Correction Methods for Landsat Imagery: Image‐Based and Model‐Based Calibration Methods

Abstract

To increase the accuracy of remotely sensed data for agricultural forecasting, pixel values must be corrected for atmospheric effects and converted to spectral reflectance. The objective of this research was to compare two atmospheric correction methods of Landsat imagery under a range of atmospheric conditions. Ground‐based dark‐object subtraction (GDOS) is an image‐based calibration method that used in situ ground data that the dark‐object subtraction (DOS) method did not use, whereas atmospheric calibration (AC) is a model‐based calibration method that required a standard atmospheric profile refined with the use of in situ atmospheric data. GDOS and AC methods improved the reflectance values and had relationships with measured bands, which were approximately 1 to 1 in all bands. However, the GDOS generally had lower root‐mean‐square errors (RMSE) than AC. Data from this study suggest that at the present time the GDOS method may be more accurate than the AC method.