江西省赣州市南康区松材线虫病发生特征

松材线虫病是我国南方森林面临的主要灾害之一。本文基于野外调查和高分一号(GF-1)卫星WFV影像数据,采用随机森林模型构建松材线虫病空间识别模型,探究地形、人类活动和林分因子等对病害发生的影响,监测病害空间分布,并采用空间自相关性分析评估江西省赣州市南康区松材线虫病发生特征。结果表明：构建模型对松材线虫病的识别效果良好(AUC值=0.99,总体精度=0.96),可以实现对区域松材线虫病空间分布情况的有效监测;归一化差异绿度指数(NDGI)、距高速公路的距离、归一化植被指数(NDVI)是重要的建模因子;空间自相关性分析表明,松材线虫病的发生存在明显的空间正相关性即空间聚集性特征;南康区松材线虫病高发生区集中于赤土乡、朱坊镇和十八塘乡,低发生区集中于蓉江街道附近;分析变量的边际效应发现,离高速公路远、离县道近的低海拔地段是松材线虫病易发区域。研究结果可服务于区域松材线虫病分布的快速监测,对该病害防治和管理具有一定的指导意义。     

松材线虫病疫木熏蒸剂筛选试验

为筛选出松材线虫病疫木的低毒熏蒸剂,采用3种熏蒸剂威百亩、棉隆、磷化铝对松材线虫病疫木进行熏蒸处理,测试3种药剂对疫木中松墨天牛和其他昆虫的杀灭效果。结果表明,威百亩的熏蒸效果明显好于棉隆、磷化铝处理组。当威百亩浓度达到200 mL/m3以上时,威百亩对松木包内部的天牛、小蠹、白蚁等均达到100%杀灭效果,实际的应用中可以考虑使用200 mL/m3的威百亩对松材线虫病疫木进行熏蒸;而棉隆对松材线虫疫木的熏蒸效果较差,天牛致死率均未达到40%,不建议使用棉隆作为松材线虫病疫木熏蒸处理剂。     

不同干扰措施对松材线虫入侵松林内物种多样性的影响

经野外调查发现:松材线虫入侵松林后,对原先林型相同的两块染病松林而言,经过人为伐除和保留受害木这两种干扰措施后,任其自然恢复更新,后恢复的林型会大不相同,即对受害木采取不同的干扰措施会对染病松林内林下植被的更新产生不同的影响.基于以上出发点,以松材线虫入侵后采取不同伐除干扰措施的2个马尾松受害群落为研究对象,针对受害木移除和保留两种处理方式,选择α多样性指数函数Rényi指数为测量单位,探讨了不同受害木处理方式下植物多样性的变化规律.结果表明:受害木及时移走的松林内林下灌草多样性比受害木保留的要高.     

利用固定翼无人机监测松材线虫病疫点枯死松树的初步研究

无人机航摄监测森林病虫害是一个新的研究热点。为探究无人机航摄在松材线虫病监测中的应用,本研究于2017年11月利用小型固定翼无人机采集了广东省河源市新丰江库区松材线虫病疫点的航摄影像,总面积1425.9 hm~2。固定翼无人机搭载了1台可见光数码相机和1台多光谱数码相机,能同时采集枯死松树的可见光和近红外的航摄影像。利用LAMapper软件对航摄图像进行空中三角测量和像素匹配,获得可见光正射影像和多光谱正射影像。使用ERDAS软件生成影像的归一化植被指数(NDVI)。然后将带有地理信息的完整影像自动导入GIS系统进行异常点识别和几何矫正,导出最终的影像数据。最后,对影像进行分析,并根据植被指数(NDVI)对图像进行分类。分析结果显示,航摄的疫点中共自动识别1486株枯死松树,并获得了其分布地图及坐标点位置。验证结果表明监测的准确率达到80%以上,坐标点精度达到2-3 m。本研究结果具有低成本、自动化、可靠、客观、高效和及时等优点,可为大面积监测松材线虫病的发生现状和流行动态、评估防控效果和灾害损失提供技术支撑。     

松材线虫(Bursaphelenchus xylophilus)入侵对马尾松(Pinus massoniana)林分生长的影响及相关生长模型

松材线虫（Bursaphelenchus xylophilus）是一种松树上发生严重的有害生物,它不仅改变了生态系统的结构和功能,而且改变了系统内生物的原有特性和地理分布。松材线虫及其引起的松树萎蔫病已对中国马尾松林（Pinus massoniana）的树木成长产生了巨大影响。基于此,使用＂每木调查法＂和＂样方法＂,对松材线虫入侵后的马尾松林内松树的各项生长指标因子进行了调查分析,其结果表明：自松材线虫1996年入侵所调查地区的松林后,对于受害松树不管是伐倒木（被伐倒）还是倒木（自然倒地）,其对周围马尾松胸径生长的影响是显著的,而对树高生长的影响不显著。最后建立了一系列的灰色和灰色-马尔可夫链数学模型,其预测结果精度高,可用于今后受害和未受害区马尾松林分因子的生长预测。     

基于多光谱影像的森林树种识别及其空间尺度响应

当前,不同空间分辨率卫星影像对森林类型识别结果中普遍存在的尺度效应,而且纹理参量对不同尺度下树种识别精度的影响仍缺乏广泛认知.本研究以中国东北旺业甸林场为研究区,采用观测时相同步、地理坐标匹配的GF-1 PMS、GF-2 PMS、GF-1 WFV,以及Landsat-8 OLI卫星传感器数据组成空间尺度观测序列(1、2、4、8、16、30 m),并结合支持向量机(SVM)模型,探讨了区域内5种优势树种遥感识别结果的尺度变化规律及其纹理特征参数的影响,同时检验了基于尺度上推转换影像的树种识别结果差异.结果表明: 影像空间分辨率对区域树种识别结果具有显著影响,其中,研究区森林树种识别的最佳影像分辨率为4 m,当分辨率降低至30 m时,树种识别结果最差.在1～8 m影像分辨率范围内,增加纹理信息能够显著提高不同优势树种的识别精度,使总分类精度提升了2.0%～3.6%,但纹理信息对16～30 m影像的识别结果没有显著影响.与真实尺度卫星影像相比,基于升尺度转换影像的树种识别结果及其尺度响应特征存在显著差异,表明在面向多个空间尺度的遥感观测和应用研究中,需要采用真实分辨率影像以确保结果的准确性.     

Fast R-CNN深度学习和无人机遥感相结合在松材线虫病监测中的初步应用研究

松材线虫病因其破坏性强、传播速度快和防治难度大等特点,严重威胁着我国的松林资源.及时发现、定位和清理病死松树是控制松材线虫病蔓延的有效手段.本研究利用小型无人机获得松材线虫病疫点的可见光和多光谱的航摄影像.根据松树针叶颜色变化,将松材线虫Bursaphelenchus xylophilus侵染的松树分为病树和枯死树两种...     

松材线虫入侵后不同伐倒干扰强度对马尾松林植物多样性的影响

以松材线虫入侵马尾松林后经过不同伐倒干扰强度经营形成的不同群落类型作为研究对象,对9个群落类型的物种多样性进行了研究.结果表明,乔木层物种多样性指数大小排列顺序为: 马尾松纯林受害皆伐后形成的阔叶林(富阳)＞轻度受害的马尾松 木荷混交林(富阳)＞对照＞轻度受害的马尾松 纯林(富阳)＞马尾松 栓皮栎混交林受害择伐后形成的栓皮栎林(舟山)＞马尾松纯林受害皆伐后形成的马尾松幼龄林(富阳)＞马尾松纯林受害择伐后形成的枫香林(舟山)＞受害的黑松 马尾松混交林(舟山)＞受害的马尾松纯林(舟山).灌木层舟山马尾松纯林的3种多样性指数均最低,其余各地相差不大.草本层马尾松幼树纯林、栓皮栎林和枫香林的3个指数较高.不同地理位置和不同受害程度的马尾松林植物多样性差异显著;不同干扰程度、不同恢复方式下马尾松林内的植物多样性差异也显著.建立了伐倒干扰强度指数,发现物种多样性指数随伐倒干扰强度指数的变化规律符合“中间高度膨胀”理论.协方差分析结果表明,所建的指数能有效地反映松材线虫入侵及病木伐除后马尾松林植物多样性的变化.     

湖北宜昌松林景观格局对松材线虫流行及扩散的影响

景观格局对能量流、物质流和物种流等生态学过程影响显著。为了探究区域生境差异对病虫害发生及扩散的影响,以湖北省宜昌市夷陵区松材线虫病为对象,结合区域森林资源二类清查矢量数据和松材线虫病普查资料,运用景观生态学的原理和方法,探究景观格局对松材线虫病发生的影响。研究结果表明:1)松林景观类型百分比、平均斑块面积、自然连接度和聚合度与松材线虫病的发病率成正相关;2)松林斑块的粒级结构分析表明,中、小斑块能抑制松材线虫病的发生,巨斑块、超大斑块对松材线虫的发生有利;3)从景观干扰上分析显示人类活动强度与松材线虫病发病率成正相关;4)在景观尺度水平上,景观的破碎度大、多样性指数高、蔓延度指数小、斑块形状简单、受人类活动影响大的乡镇松材线虫病发病率高。通过斑块类型尺度和景观尺度两个水平上的分析可知,在夷陵区乡镇尺度上,由小斑块松林组成且斑块聚集度低、景观破碎化程度低的景观格局对松材线虫病有一定的抑制作用。研究结论对当地松材线虫病的防治就有较好的参考价值。     

松材线虫及其关键传媒墨天牛的研究进展

松材线虫Bursaphelenchusxylophilus (Steiner&Buhere,1 93 4Nickle,1 981 )是一种世界多国公认的重大外来生物。其原产地在美国 ,但松材线虫并不严重危害该国松林 ;日本受害最重 ,经过几十年的研究与防治 ,现已基本能控制松材线虫病大发生。自 1 982年我国南京中山陵首次发现松材线虫以来 ,其在我国的扩散趋势越来越明显 ,现已成为我国一种重要入侵病原生物。它不但对我国南方数百万公顷松林构成毁灭性威胁 ,影响我国经济和社会可持续发展 ,而且将破坏我国一些著名风景名胜区、文化遗产地。同时 ,松材线虫正成为一项技术壁垒 ,严重影响我国的进出口贸易。该文简要从松材线虫及其关键传煤墨天牛Monochamusspp .的生物学特性、分布状况 ,松材线虫病的蔓延条件及影响因素等方面概述国内外的研究动态 ,以期为我国对松材线虫的研究与防治工作提供参考     

Evaluation and comparison of the earth observing sensors in land cover/land use studies using machine learning algorithms

The rapid transformation of land cover/land use (LCLU) is a strong indication of global environmental change. In order to monitor LCLU through maps, a significant dataset and robust technique are necessary. Thus, the primary objective of the current research is to evaluate and compare the efficiency of several notable satellite sensors including Landsat-8 (L-8), Sentinel-2 (S-2), Sentinel-1 (S-1), combined Sentinel-1 and Sentinel-2 (S-1-2), LISS III (L-3), and LISS IV (L-4) for LCLU mapping applying random forest (RF), logit boost (LB), stochastic gradient boosting (SGB), artificial neural network (ANN), and K-nearest neighbor (KNN) models. For this purpose, 300 samples for each of the six LCLU classes have been selected based on field survey and high resolution Cartosat-3 images. The classification accuracy namely producer accuracy (PA), user accuracy (UA), overall accuracy (OA) and kappa coefficient have been calculated from the confusion matrix of the applied models. This results show the highest accuracy has been derived from the integration of S-1-2 datasets followed by S-2, L-8, L-3, L-4, and S-1. On the other hand, LB model is the most consistent and efficient in comparison with other models for all the datasets. Regarding importance of variable, SWIR band is repeatedly the most crucial factor while blue band is the least significant variable. From this comparative assessment of sensors, it has been found that high spatial and spectral resolutions along with combination of satellite datasets are required to get better accuracy rather than only high spatial resolution in regional scale mapping. The present study strongly advocates the use of combined S-1-2 data together with the application of LB model for LCLU classification.     

Hierarchical Bayesian geostatistics for C stock prediction in disturbed plantation forest in Zimbabwe

We develop and present a novel Bayesian hierarchical geostatistical model for the prediction of plantation forest carbon stock (C stock) in the eastern highlands of Zimbabwe using multispectral Landsat-8 and Sentinel-2 remotely sensed data. Specifically, we adopt a Bayesian hierarchical methodology encompassing a model-based inferential framework making use of efficient Markov Chain Monte Carlo (MCMC) techniques for assessing model input parameters. Our proposed hierarchical modelling framework evaluates the influence of two but related covariate information sources in C stock prediction in order to build sustainable capacity on carbon reporting and monitoring. The perceived improvements in the spectral and spatial properties of Landsat-8 and Sentinel-2 data and their potential to predict C stock with shorter uncertainty bounds is tested in the developed hierarchical Bayesian models. We utilized the Mean Squared Shortest Distance (MSSD) as the objective function for optimization of sampling locations for equal area coverage. Specifically, we evaluated the models using four selected remotely sensed vegetation indices namely, the normalised difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), enhanced vegetation index (EVI) and an additional distance to settlements anthropogenic variable that justifies from the history of the studied plantation forest in the eastern highlands of Zimbabwe. We evaluated two models making use of Landsat-8 and Sentinel-2 derived predictors using the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Coverage (CVG) and Deviance Information Criteria (DIC). The Sentinel-2 based C stock model resulted in RMSE of 1.16 MgCha⁻¹, MAE of 1.11 MgCha⁻¹, CVG of 94.7% and a DIC of −554.7 whilst its Landsat-8 based C stock counterpart yielded a RMSE, MAE, CVG and DIC of 2.69 MgCha⁻¹, 1.77 MgCha⁻¹, 85.4% and 43.1 respectively. Although predictive models from both sensors show great improvement in predictive accuracy when modelling the spatial random effects, the Sentinel-2 based C stock predictive model substantially outperforms its Landsat-8 based C stock counterpart. The Sentinel-2 based C stock predictive hierarchical model therefore adequately addresses multiple sources of uncertainty inherent in the spatial prediction of C stock in disturbed plantation ecosystems. It is evident from the results of this study that carbon reporting and monitoring can always be improved by scouting for improved and easily accessible remote sensing data and allow forest practitioners to keep track of error across space in resource environments of interest.     

基于实测高光谱与Sentinel-2B数据的银北土壤Na+含量估测

为了探讨不同传感器对土壤Na⁺含量的估测能力,本研究以宁夏银北地区典型样点土壤实测光谱和Sentinel-2B影像光谱为对象,运用逐步回归(SR)和主成分回归分析(PCA)方法对光谱数据进行敏感参量筛选,然后采用偏最小二乘回归(PLSR)、支持向量机(SVM)和反向传播神经网络模型(BPNN)分别建立实测光谱和影像数据的土壤Na⁺含量估算模型。结果表明: 除Band9外,实测重采样数据与影像数据呈极显著相关。基于SR筛选方式建立的模型估算精度普遍高于PCA(SVM模型除外),PCA-SVM模型为影像最佳Na⁺含量估算模型,预测精度为0.792;SR-BPNN模型为实测最佳Na⁺含量估算模型,预测精度达到0.908。经重采样实测光谱模型校正后的SR-PLSR影像光谱土壤Na⁺含量估算模型精度从0.481提高到0.798,有效提高了较大尺度下的土壤Na⁺含量估算精度。本研究实现了遥感监测土壤Na⁺含量由点向面的空间转换,为Sentinel-2B影像监测盐渍化土壤Na⁺含量提供了科学参考。     

Field-scale rice yield prediction from Sentinel-2 monthly image composites using machine learning algorithms

Machine learning (ML) along with high volume of satellite images offers an alternative to agronomists in crop yield predictions for decision support systems. This research exploited the possibility of using monthly image composites from Sentinel-2 imageries for rice crop yield predictions one month before the harvesting period at the field level using ML techniques in Taiwan. Three ML models, including random forest (RF), support vector machine (SVM), and artificial neural networks (ANN), were designed to address the research question of yield predictions in four consecutive growing seasons from 2019 to 2020 using field survey data. The research findings of yield modeling and predictions showed that SVM slightly outperformed RF and ANN. The results of model validation, obtained from SVM models using the data from transplanting to ripening, showed that the root mean square percentage error (RMSPE) and the mean absolute percentage error (MAPE) values were 5.5% and 4.5% for the 2019 second crop, and 4.7% and 3.5% for the 2020 first crop, respectively. The results of yield predictions (obtained from SVM) for the 2019 second crop and the 2020 first crop evaluated against the government statistics indicated a close agreement between these two datasets, with the RMSPE and MAPE values generally smaller than 11.2% and 9.2%. The SVM model configuration parameters used for rice crop yield predictions indicated satisfactory results. The comparison results between the predicted yields and the official statistics showed slight underestimations, with RMSPE and MAPE values of 9.4% and 7.1% for the 2019 first crop (hindcast), and 11.0% and 9.4% for the 2020 second crop (forecast), respectively. This study has successfully proven the validity of our methods for yield modeling and prediction from monthly composites from Sentinel-2 imageries using ML algorithms. The research findings from this research work could useful for agronomists to timely formulate action plans to address national food security issues.     

An algorithm for early rice area mapping from satellite remote sensing data in southwestern Guangdong in China based on feature optimization and random Forest

Estimating of rice areas using images obtained from satellite remote sensing is important for guiding operators. The object of this study was the Sentinel-2A/B image data of the rice planting demonstration regions in southwestern Guangdong, China. We designed an algorithm for early rice area mapping based on feature optimization and random forest (RF). For modeling, we selected 35 common remote sensing features and applied out-of-bag (OOB) to construct 7 feature combinations. The results showed that the overall accuracy (OA) and Kappa coefficient of the RF with the best combination were 91.23% and 87.55%, respectively. Compared with support vector machine (SVM) and back propagation neural network (BPNN), the model result of RF was also the best among the three. Additionally, the maximum error of the rice area was less than 16% when the model was transferred to other regions in Guangdong. The feature optimization and RF-based algorithm proposed in this study can effectively map the early rice region. It can be applied to estimate rice area based on satellite remote sensing image data and reveal the ecological status of rice cultivation in southwestern Guangdong.     

基于不同空间尺度遥感影像估算森林叶面积指数的差异

地面测量点对遥感像元的代表性如何,怎样获取像元的相对真值,多大的空间分辨率可以真实地反映森林区域的叶面积指数(LAI),这些都是定量遥感中的重要问题.本研究计算LAI-2200和TRAC两种冠层分析仪测量的空间范围,并结合GF-2(4.1 m)、Sentinel-2(10 m)、Landsat-8(30 m)3种不同空间分辨率遥感影像,找到各尺度下像元的相对真值,在保持真值观测面积和遥感获取面积一致的条件下,基于一元指数和多元回归模型,对比分析不同空间分辨率影像对估算森林LAI的影响,并对3种影像模型进行30和100 m尺度下的检验以及各自数据集的空间代表性评价,比较得出最适合表达研究区域森林LAI的尺度.结果表明:对于森林来说,高分辨率并不一定能充分反映森林LAI.基于3种分辨率影像的统计模型都能很好地估测森林LAI,其中,基于Sentinel-2的反演精度最高,基于GF-2的反演精度最低.30和100 m尺度下的检验结果表明,基于GF-2反演模型高估了森林LAI,基于Landsat-8的反演模型低估了森林LAI,基于Sentinel-2分辨率的统计模型可以很好地估测研究区域森林LAI.     

Mono-temporal and multi-temporal approaches for burnt area detection using Sentinel-2 satellite imagery (a case study of Rokan Hilir Regency,Indonesia)

Accurate and up-to-date information about the burnt area is important in estimating environmental losses, prioritizing rehabilitation areas, and determining future planning strategies. The publicly available medium resolution optical Sentinel-2 satellite data provides a practical and effective solution for burnt area detection. In this study, we proposed two different approaches using mono-temporal and multi-temporal Sentinel-2 satellite imagery to detect burnt areas in Rokan Hilir Regency, Indonesia. The multi-temporal approaches utilized two different ensemble machine learning algorithms (Random Forest and XGBoost) and used six composite spectral indices of the differenced Normalized Burn Ratio (dNBR), differenced Normalized Burn Ratio 2 (dNBR2), differenced Normalized Difference Vegetation Index (dNDVI), differenced Soil Adjusted Vegetation Index (dSAVI), differenced Char Soil Index (dCSI), differenced Burnt area Index for Sentinel-2 (dBAIS2), and differenced Mid-infrared Burn Index (dMIRBI) as model inputs. The burnt areas are labeled by combining hotspots with confidence intervals above 95%, fire spots, and change detection methods. The XGBoost model achieved the best performance with an F1 score of 0.97 and an accuracy of 96%. Furthermore, we use the SHapley Additive exPlanations (SHAP) to quantify the contribution of each feature as well as its correlation with the target class. The dNBR, dMIRBI, and dNBR2 indices contribute the most to the XGBoost model. In comparison, this study also investigates and compares a mono-temporal approach with One-dimensional Convolutional Neural Network (CNN-1D) architecture and the performance obtained is slightly better than both machine learning models. Overall, both mono-temporal and multi-temporal approaches satisfactorily detect the burnt area.     

Machine learning algorithms to predict the 1 year unfavourable prognosis for advanced schistosomiasis

Short-term prognosis of advanced schistosomiasis has not been well studied. We aimed to construct prognostic models using machine learning algorithms and to identify the most important predictors by utilising routinely available data under the government medical assistance programme. An established database of advanced schistosomiasis in Hunan, China was utilised for analysis. A total of 9541 patients for the period from January 2008 to December 2018 were enrolled in this study. Candidate predictors were selected from demographics, clinical features, medical examinations and test results. We applied five machine learning algorithms to construct 1 year prognostic models: logistic regression (LR), decision tree (DT), random forest (RF), artificial neural network (ANN) and extreme gradient boosting (XGBoost). An area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance. The important predictors of the optimal model for unfavourable prognosis within 1 year were identified and ranked. There were 1249 (13.1%) cases having unfavourable prognoses within 1 year of discharge. The mean age of all participants was 61.94 years, of whom 70.9% were male. In general, XGBoost showed the best predictive performance with the highest AUC (0.846; 95% confidence interval (CI): 0.821, 0.871), compared with LR (0.798; 95% CI: 0.770, 0.827), DT (0.766; 95% CI: 0.733, 0.800), RF (0.823; 95% CI: 0.796, 0.851), and ANN (0.806; 95% CI: 0.778, 0.835). Five most important predictors identified by XGBoost were ascitic fluid volume, haemoglobin (HB), total bilirubin (TB), albumin (ALB), and platelets (PT). We proposed XGBoost as the best algorithm for the evaluation of a 1 year prognosis of advanced schistosomiasis. It is considered to be a simple and useful tool for the short-term prediction of an unfavourable prognosis for advanced schistosomiasis in clinical settings.     

Identification of Sunn-pest affected (Eurygaster Integriceps put.) wheat plants and their distribution in wheat fields using aerial imaging

Sunn pest (Eurygaster integriceps put.) causes severe damage to wheat fields annually, reducing production by up to 50%. Rapid identification of pest concentration points and estimation of infestation levels in fields can be useful for production management and reducing the use of chemical sprays. Because of the limited ability to detect pests on the ground and access to high-resolution satellite imagery, aerial photography was considered for crop pest and disease detection. In this study, the feasibility of soft computing approaches and image processing to identify areas infected with sunn pest using near-infrared and visible light aerial imagery was investigated. An irrigated winter wheat field was surveyed for five consecutive months, from February to June. The spectral vegetation features (SVI), were extracted and analysed for both near infrared and visible light images. To detect infected spikes, Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel was used. The Red and near-infrared (NIR) bands reflectance and, the Ratio Vegetation Index (RVI) for near-infrared images as well as Red and Green bands reflectance and normalised green blue difference index (NGBDI) for visible light images had the greatest impact on the performance of the SVM classifiers. The SVM classifiers were validated using the confusion matrix method. The best accuracy and performance of the detection system was achieved in February and March when the healthy wheat plant was still green. The mean accuracy for these two months was 0.97 and 0.93 for the SVM classifiers for NIR and visible light, respectively.