基于PlanetScope影像的典型绿洲土壤盐渍化数字制图

干旱半干旱地区急需高分辨率的土壤盐度图用于显示盐度空间分布的细微变化,指导盐渍化区域和潜在盐渍化区域制定土地资源管理政策和水资源管理政策,防止土壤进一步退化,保障农业经济可持续发展和粮食安全生产。基于PlanetScope影像,提取植被光谱指数和土壤盐度指数,共计21个变量,将其输入装袋回归(Bootstrap aggregating,Bagging)算法中,构建了土壤盐度预测模型Model-Ⅰ;使用最相关最小冗余(Max-relevance and min-redundancy,mRMR)方法筛选特征变量,将其输入Bagging中,构建了土壤盐度预测模型Model-Ⅱ,使用野外采样数据来辅助建模并进行验证。通过模型评价指标对Model-Ⅰ和Model-Ⅱ进行评估。结果表明:Model-Ⅱ的预测性能优于Model-Ⅰ(验证集决定系数为0.66,均方根误差为18.00 dS·m-1,四分位数的相对预测误差为3.21),mRMR有效降低了多维特征冗余问题。PlanetScope影像结合mRMR方法成功绘制了高分辨率土壤盐度图,提供了更详细的土壤盐度空间分布信息,研究结果对利用PlanetScope数据监测土壤盐渍化信息起推动作用。

基于PlanetScope影像的格陵兰冰面融水监测

格陵兰冰盖的消融及其对海平面上升的贡献成为国际上研究的热点。每年消融期,格陵兰冰盖表面消融,融水会导致冰面形成冰面湖、冰面河、注水冰裂隙等形态。格陵兰冰面融水规模庞大、结构复杂、变化迅速,区域气候模型难以准确模拟冰面融水分布,中等分辨率卫星影像难以反映冰面融水的时空变化。以PlanetScope为代表的CubeSat小卫星空间分辨率高达3 m,理想情况下重访周期可达1 d,这为精细化动态监测格陵兰冰面融水提供了可能。本研究利用PlanetScope高空间分辨率小卫星遥感影像提取格陵兰冰盖西南部典型流域冰面融水遥感信息,构建了针对PlanetScope遥感影像的冰面融水深度反演公式,对比了MAR v3.11区域气候模型模拟的融水径流量与遥感反演的融水体积。结果表明:在2019年7—8月,流域内冰面融水开放水体比率先上升后下降,在7月12日达到峰值8.7%;流域内冰面融水深度介于0.2~1.5 m之间,冰面湖最深(0.9 m±0.2 m),冰面河干流次之(0.6 m±0.1 m),冰面河支流最浅(0.5 m±0.1 m);遥感观测的开放水体比率、冰面融水体积与区域气候模型MAR模拟的融水日径流量具有正相关关系,故融水径流对于冰面湖与冰面河具有直接供给作用;流域冰面融水存储比例(遥感观测的冰面融水体积与模型模拟的融水累积径流量之比)先升高后降低,冰面融水储存比例小于1%,储存能力十分有限,冰面流域能够高效输送融水进入冰盖内部。

Planetscope Nanosatellites Image Classification Using Machine Learning

To adopt sustainable crop practices in changing climate, understandingthe climatic parameters and water requirements with vegetation is crucial on aspatiotemporal scale. The Planetscope (PS) constellation of more than 130 nanosatellites from Planet Labs revolutionize the high-resolution vegetation assessment. PS-derived Normalized Difference Vegetation Index (NDVI) maps areone of the highest resolution data that can transform agricultural practices andmanagement on a large scale. High-resolution PS nanosatellite data was utilizedin the current study to monitor agriculture’s spatiotemporal assessment for theAl-Qassim region, Kingdom of Saudi Arabia (KSA). The time series of NDVIwas utilized to assess the vegetation pattern change in the study area. The currentstudy area has sparse vegetation, and exposed soil exhibits brightness due to lowsoil moisture, constraining NDVI. Therefore, a machine learning (ML) basedRandom Forest (RF) classification model was used to compare the vegetationextent and computational cost of NDVI. The RF model has been compared withNDVI in the current investigation. It is one of the most precise classificationmethods because it can model the complexity of input variables, handle outliers,treat noise effectively, and avoid overfitting. Multinomial Logistic Regression(MLR) was implemented to compare the performance of both NDVI and RFbased classification. RF model provided good accuracy (98%) for all vegetationclasses based on user accuracy, producer accuracy, and kappa coefficient.

Fusion of Landsat 8 OLI and PlanetScope Images for Urban Forest Management in Baton Rouge, Louisiana

In recent years image fusion method has been used widely in different studies to improve spatial resolution of multispectral images. This study aims to fuse high resolution satellite imagery with low multispectral imagery in order to assist policymakers in the effective planning and management of urban forest ecosystem in Baton Rouge. To accomplish these objectives, Landsat 8 and PlanetScope satellite images were acquired from United States Geological Survey (USGS) Earth Explorer and Planet websites with pixel resolution of 30m and 3m respectively. The reference images (observed Landsat 8 and PlanetScope imagery) were acquired on 06/08/2020 and 11/19/2020. The image processing was performed in ArcMap and used 6-5-4 band combination for Landsat 8 to visually inspect healthy vegetation and the green spaces. The near-infrared (NIR) panchromatic band for PlanetScope was merged with Landsat 8 image using the Create Pan-Sharpened raster tool in ArcMap and applied the Intensity-Hue-Saturation (IHS) method. In addition, location of urban forestry parks in the study area was picked using the handheld GPS and recorded in an excel sheet. This sheet was converted into Excel (.csv) file and imported into ESRI ArcMap to identify the spatial distribution of the green spaces in East Baton Rouge parish. Results show fused images have better contrast and improve visualization of spatial features than non-fused images. For example, roads, trees, buildings appear sharper, easily discernible, and less pixelated compared to the Landsat 8 image in the fused image. The paper concludes by outlining policy recommendations in the form of sequential measurement of urban forest over time to help track changes and allows for better informed policy and decision making with respect to urban forest management.

Combining PlanetScope and Sentinel-2 images with environmental data for improved wheat yield estimation

Satellite images are widely used for crop yield estimation,but their coarse spatial resolution means that they often fail to provide detailed information at thefield scale.Recently,a new generation of high-resolution satellites and CubeSat platforms has been launched.In this study,satellite data sources including PlanetScope and Sentinel-2 were combined with topographic and climatic variables,and the improvement in wheat yield estimation was evaluated.Wheat yield data from a combine harvester were used to train and validate a yield estimation model based on random forest regression.Nine vegetation indices(NDVI,GNDVI,MSAVI2,MTVI2,MTCI,reNDVI,SAVI,EVI and WDVI)and spectral bands were tested.During the model training,the Sentinel-2 data realized a slightly higher estimation accuracy than the PlanetScope data.However,combining environmental data with the PlanetScope data realized the highest estimation accuracy.For the validated models,adding the topographic and climatic datasets to the satellite data sources improved the estimation accuracy,and the results were slightly better with the Sentinel-2 data than with the PlanetScope data.Observation data of the milk and dough stages provided the highest estimation accuracy of the wheat yield at 210–225 days after sowing.

基于PlanetScope影像的广西钦州市黑臭水体识别方法研究

城市黑臭水体实质上是由环境保护和城市建设两者发展不平衡产生的,也是我国当下生态环境保护工作的重点之一。针对城市黑臭水体监测评价这一热点难点展开研究,以钦州市主城区为研究区域,以高频次重访的高空间分辨PlanetScope遥感影像为数据源,结合两期的实地采样数据,分析黑臭水体表观光学特性,利用黑臭水体与一般水体光谱曲线差异特征,提出近红外(NIR)单波段阈值法、HI指数法、EHI指数法和NDBWI指数法以及基于色度法的饱和度识别算法。城市黑臭水体与一般水体在蓝、绿和红波段(455~670 nm)的相同点是反射率偏低,不同点在于一般水体在455~670 nm处的光谱曲线斜率高于黑臭水体,在红波段处反射率达到极大值,在红波段和近红外波段开始下降,而黑臭水体此波段范围内反射率开始大幅升高。识别结果表明,NIR单波段阈值法识别准确率较低,存在较大偏差;HI指数识别准确率为57.14%;EHI指数和饱和度法对黑臭水体的识别准确率均为78.57%;NDBWI指数的识别准确率最高,达90%以上。

利用多特征深度学习模型的同震滑坡智能化提取

同震滑坡的智能化提取是地震后应急救援和风险评估的重要手段.然而,具有相似光谱特征的道路和裸地等地面物体总是干扰同震滑坡的精准遥感提取,从而使得现有方法难以快速和准确地收集同震滑坡信息并评估其影响.为提高同震滑坡提取的准确度,本研究提出了一种基于多种滑坡识别特征数据集的深度学习模型(ENVINet5_MF)用以自动提取同震滑坡. ENVINet5_MF在构建的过程中结合了滑坡增益指数(LGI),该指数能够扩大同震滑坡与裸地和道路之间的特征差异,有利于消除来自裸地和道路对同震滑坡提取的干扰.利用多时相Planet Scope图像,以日本北海道同震滑坡和中国米林同震滑坡为研究对象,分别在这两个区域进行了同震滑坡智能化提取实验.提取结果和方法性能评估表明ENVINet5_MF取得了比对比方法更加优异的性能,即ENVINet5_MF检测到的同震滑坡与地面参考数据最吻合,并且ENVINet5_MF的精度高于对比方法以及耗时最短.本研究提出的ENVINet5_MF大大提高了同震滑坡提取的准确性,为同震滑坡提取提供了一种高效的方法,可满足同震滑坡灾害的快速响应.

Quick and automatic detection of co-seismic landslides with multifeature deep learning model

Co-seismic landslide detection is essential for post-disaster rescue and risk assessment after an earthquake event.However,a variety of ground objects,including roads and bare land,have spectral characteristics similar to those of co-seismic landslides,making it difficult to gather information and assess their impact rapidly and accurately.Therefore,an automatic detection method based on a deep learning model,named ENVINet5,with multiple features(ENVINet5_MF)was proposed to solve this problem and improve the detection accuracy of co-seismic landslides.The ENVINet5_MF method is advantageous for co-seismic landslide detection because it features a landslide gain index(LGI)that effectively eliminates the spectral interference of bare land and roads.We conducted two experiments using multi-temporal PlanetScope images acquired in Hokkaido,Japan,and Mainling,China.The accuracy evaluation and rationality analysis show that ENVINet5_MF performed better than comparative methods and that the co-seismic landslide areas detected by ENVINet5_MF were the most consistent with ground reference data.The findings of this study suggest that ENVINet5_MF can provide an efficient and accurate method for coseismic landslide detection to ensure a rapid response to co-seismic landslide disasters.

基于决策树的城市黑臭水体遥感分级

水体黑臭程度遥感监测是了解城市水质现状和综合评价城市水环境治理效果的重要手段.以南京、常州、无锡和扬州为研究区,共采集171个样点,同步测量水质参数和光学参数,分析黑臭水体与一般水体的水色和光学特征,构建决策树模型进行重度黑臭水体、轻度黑臭水体和非黑臭水体(记为一般水体)识别.结果表明:(1)根据色度可将水体分为1~6类水体,其中,类型1~4为黑臭水体,分别为灰黑色、深灰色、灰色和浅灰色水体,类型5和类型6水体为一般水体,分别为绿色系和黄色系水体;(2)类型1水体的非色素颗粒物和有色可溶性有机物含量高,但色素颗粒物的吸收并不占主导,类型2和5水体的吸收以色素颗粒物吸收占主导,类型3、4和6水体的吸收以非色素颗粒物吸收占主导;(3)根据六类水体的反射光谱差异用黑臭水体差值指数(difference of black-odorous water index,DBWI)、三波段面积水体指数(green-red-nir area water index,G-R-NIR AWI)、绿光波段反射率和归一化黑臭水体指数(normalized difference black-odorous water index,NDBWI)构建的水体分类识别决策树,能够有效识别出重、轻度黑臭水体和一般水体;(4)将决策树模型应用于2019年4月9日扬州的PlanetScope影像上,并利用10个同步过境点进行验证,整体识别精度达到80.00%,K值达到0.67.通过水色分类后的城市水体分级模型方法,可推广应用于类似的水体,为黑臭水体监管提供技术方法.

面向城市土地利用的高分辨率遥感特征分析

针对分类特征选取问题,分析了PlanetScope影像的城市地物特征对于分类结果的影响,并以江西省南昌市作为实证研究。探究13类城市地物的光谱、纹理、形状特征,以及植被指数和空间关系,提取不同地物的优势特征进行规则的决策树分类,并将分类结果与支持向量机和随机森林两种分类方法进行比较。研究结果发现:河流、沟渠和道路等线状地物的形状特征显著;植被间(林地与田地)的纹理特征差异明显;建筑物分布密集、形状规则,不同材质的建筑屋顶光谱特征存在差异,亮度值与形状特征对于该类地物显著性较高。3种方法的分类总体精度和Kappa系数分别为95.9%和95.5%,精度优于RF(80.4%)和SVM(76.2%),发现基于规则的决策树方法更适合于城市的密集性地物分类,清楚地展示了城市地物适用的分类特征,为小卫星数据的城市土地利用分类提供了参考和借鉴价值。