Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning

The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.

Land subsidence induced by groundwater extraction and building damage level assessment—a case study of Datun, China

As in many parts of the world, long-term excessive extraction of groundwater has caused significant land-surface sub- sidence in the residential areas of Datun coal mining district in East China. The recorded maximum level of subsidence in the area since 1976 to 2006 is 863 mm, and the area with an accumulative subsidence more than 200 mm has reached 33.1 km2 by the end of 2006. Over ten cases of building crack due to ground subsidence have already been observed. Spatial variation in ground subsi- dence often leads to a corresponding pattern of ground deformation. Buildings and underground infrastructures have been under a higher risk of damage in locations with greater differential ground deformation. Governmental guideline in China classifies build- ing damages into four different levels, based on the observable measures such as the width of wall crack, the degree of door and window deformation, the degree of wall inclination and the degree of structural destruction. Building damage level (BDL) is esti- mated by means of ground deformation analysis in terms of variations in slope gradient and curvature. Ground deformation analysis in terms of variations in slope gradient has shown that the areas of BDL III and BDL II sites account for about 0.013 km2 and 0.284 km2 respectively in 2006, and the predicted areas of BDL (define this first) III and II sites will be about 0.029 km2 and 0.423 km2 respectively by 2010. The situation is getting worse as subsidence continues. That calls for effective strategies for subsidence miti- gation and damage reduction, in terms of sustainable groundwater extraction, enhanced monitoring and the establishment of early warning systems.

Classification and Extraction of Urban Land-Use Information from High-Resolution Image Based on Object Multi-features

Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.

Subsidence associated with land use changes in urban aquifers with intensive extraction

Land use change is a major factor in alterations in natural processes and cycles. Remote sensing has become an excellent tool to evaluate technological changes in land cover and land use changes over large areas, such as those occurring in the Valley of San Luis Potosi (VSLP). Here, such changes have impacted a system which is 95% dependent on the aquifer. The methodology for the present study is based on the use of satellite images for the years 1976, 1986, 1995 and 2000. To asses land use change, a supervised classification process was used with a decision tree technique and ENVI 4.3 software. The evolution of groundwater levels for the years 1977, 1986, 1995, 1998 and 2007 was also analyzed, as well as problems of subsidence and fissuring in the urban area of the valley in 2006. With the support of remote sensing, it was possible to analyze the dynamic changes in land use over large areas and highlight their impact on the environment.

Robust Cultivated Land Extraction Using Encoder-Decoder

Cultivated land extraction is essential for sustainable development and agriculture.In this paper,the network we propose is based on the encoder-decoder structure,which extracts the semantic segmentation neural network of cultivated land from satellite images and uses it for agricultural automation solutions.The encoder consists of two part:the first is the modified Xception,it can used as the feature extraction network,and the second is the atrous convolution,it can used to expand the receptive field and the context information to extract richer feature information.The decoder part uses the conventional upsampling operation to restore the original resolution.In addition,we use the combination of BCE and Loves-hinge as a loss function to optimize the Intersection over Union(IoU).Experimental results show that the proposed network structure can solve the problem of cultivated land extraction in Yinchuan City.

Development of Novel Water-extraction System with Thermoelectric Module Using Solar and Wind Power in Arid Land

This study aimed to develop a water-extraction system which could produce the fresh water from the air in arid regions and which used renewable energies as the electric power source. In this paper, the experiments for water extraction from the air were carried out by using the novel multi-stage water-extraction device with Peltier deices for two cases of temperature and related humidity of the air. One was the case where the temperature and the related humidity of the air were constant, and the other was the case where they were simulated the variation of the temperature and related humidity of the air in a day of summer and spring in Loess Plateau, China. The effects of the temperature and related humidity of the atmospheric air and supply the electric power to Peltier devices on performance of water production of the device were investigated and reported.

Analysis of the Relationship between Land Surface Temperature and Vegetation and Built-Up Indices in Upper-Hill, Nairobi

Designing “liveable” cities as climate change effects are felt all over the world has become a priority to city authorities as ways are sought to reduce rising temperatures in urban areas. Urban Heat Island (UHI) effect occurs when there is a difference in temperature between rural and urban areas. In urban areas, impervious surfaces absorb heat during the day and release it at night, making urban areas warmer compared to rural areas which cool faster at night. This Urban Heat Island effect is particularly noticeable at night. Noticeable negative effects of Urban Heat Islands include health problems, air pollution, water shortages and higher energy requirements. The main objective of this research paper was to analyze the spatial and temporal relationship between Land Surface Temperature (LST) and Normalized Density Vegetation Index (NDVI) and Built-Up Density Index (BDI) in Upper-Hill, Nairobi Kenya. The changes in land cover would be represented by analyzing the two indices NDVI and BDI. Results showed the greatest increase in temperature within Upper-Hill of up to 3.96&#176C between the years 2015 and 2017. There was also an increase in impervious surfaces as indicated by NDVI and BDI within Upper-Hill and its surroundings. The linear regression results showed a negative correlation between LST and NDVI and a positive correlation with BDI, which is a better predictor of Land Surface Temperature than NDVI. Data sets were analyzed from Landsat imagery for the periods 1987, 2002, 2015 and 2017 to determine changes in land surface temperatures over a 30 year period and it’s relation to land cover changes using indices. Visual comparisons between Temperature differences between the years revealed that temperatures decreased around the urban areas. Minimum and maximum temperatures showed an increase of 1.6&#176C and 3.65&#176C respectively between 1987 and 2017. The comparisons between LST, NDVI and BDI show the results to be significantly different. The use of NDVI and BDI to study changes in land cover due to urbanization, reduces the time taken to manually classify moderate resolution satellite imagery.

Research on Extraction Method of Surface Information Based on Multi-Feature Combination Such as Fractal Texture

Because of the developed economy and lush vegetation in southern China, the following obstacles or difficulties exist in remote sensing land surface classification: 1) Diverse surface composition types;2) Undulating terrains;3) Small fragmented land;4) Indistinguishable shadows of surface objects. It is our top priority to clarify how to use the concept of big data (Data mining technology) and various new technologies and methods to make complex surface remote sensing information extraction technology develop in the direction of automation, refinement and intelligence. In order to achieve the above research objectives, the paper takes the Gaofen-2 satellite data produced in China as the data source, and takes the complex surface remote sensing information extraction technology as the research object, and intelligently analyzes the remote sensing information of complex surface on the basis of completing the data collection and preprocessing. The specific extraction methods are as follows: 1) extraction research on fractal texture features of Brownian motion;2) extraction research on color features;3) extraction research on vegetation index;4) research on vectors and corresponding classification. In this paper, fractal texture features, color features, vegetation features and spectral features of remote sensing images are combined to form a combination feature vector, which improves the dimension of features, and the feature vector improves the difference of remote sensing features, and it is more conducive to the classification of remote sensing features, and thus it improves the classification accuracy of remote sensing images. It is suitable for remote sensing information extraction of complex surface in southern China. This method can be extended to complex surface area in the future.

基于Landsat的环洞庭湖区湿地信息提取

大范围湿地信息的精细提取对湿地资源的管理和保护具有关键作用。基于GEE平台和ArcGIS软件,对Google云端提供的Landsat数据进行预处理后,分别采用最小距离、决策树、随机森林、迭代决策树4种不同类型的分类器提取环洞庭湖区域的湿地信息。主要研究结果如下:随机森林分类方法得出的分类结果的精度最高,总体精度(OA)为95.82%,Kappa系数为0.942;最终提取得到2015年环洞庭湖区湿地的各个地类中,水体(河流、湖泊、库塘)、苔草滩地、泥沙滩地、芦苇滩地的面积占比分别为6.385%、4.578%、0.418%、6.060%。研究结果可为大面积湿地的监测和分类工作提供更高效的技术支持和更可靠的数据保障。

基于Landsat ETM+影像的增强型裸地指数研究

针对当前大多数裸地提取指数未考虑高反射率建筑与裸地在ETM+遥感影像上的光谱相似性的问题,该文通过分析高反射率建筑与裸地的波谱特性,构建了裸地区域指数(BAI)和简化裸地区域指数(SBAI),并使用土壤调节植被指数(SAVI)和改进的归一化差值水体指数(MNDWI)消除了植被和水体的影响。在此基础上,引用建筑指数(IBI),通过指数函数图像拉伸的方法,增大裸地在BAI/SBAI与IBI上的差异,提出了增强型裸地区域指数(EBAI)和增强型简化裸地区域指数(ESBAI),将裸地正值化、背景地物负值化,克服了大多数裸地指数阈值难以确定且易受噪声影响、精度差的缺点。实验结果表明,同参与对比的指数中具有最高精度的NDBaI相比,ESBAI生产者精度和使用者精度分别提升了10.26%、9.18%,EBAI分别提升了8.08%、7.78%。

中分辨率遥感影像土地利用覆被信息自动提取研究——以太原市区Landsat8影像为例

"土地利用/土地覆被"(简称LUCC)是全球环境变化研究的热点问题之一,遥感技术是LUCC研究的重要手段,遥感影像LUCC信息的高精度自动提取成为众多专家学者关注的重要研究领域.Landsat系列卫星影像是最早且最为广泛使用的中分辨率陆地遥感影像.文章以2013年2月发射的Landsat8卫星的OLI影像为研究对象,利用ENVI软件,对太原市区的土地利用/土地覆被信息分别用最大似然法和决策树分类法实现自动提取,并进行精度比较.结果表明:最大似然法提取的总体精度为69.33%,Kappa系数为0.605 5,主要是耕地与林地、草地、建设用地以及建设用地与裸地的混分、错分现象较为严重,造成分类精度较低;而决策树分类法的自动提取通过确定适当的判别规则,使地类间的混分、错分现象明显改善,分类总体精度提高到91.33%,Kappa系数达到0.892 3,各土地利用类型的分类精度均有一定提高.

Landsat8不透水面遥感信息提取方法对比

不透水面是重要的地表覆盖类型,利用卫星遥感影像准确提取不透水面信息对于掌握地表覆盖变化具有重要意义。现有研究已提出了多种不透水面遥感信息提取指数,但目前尚缺乏对这些不透水面指数的系统对比分析。利用Landsat8卫星遥感影像,测试了目前8种主要不透水面指数的提取精度。结果表明,在现有不透水面指数中,垂直不透水层指数能够有效增强不透水面信息,不透水面提取精度最高(89.6%),其次是比值居民地指数和生物物理组分指数(87.5%和87.4%),城市指数与新建筑指数提取精度再次之(82.9%和80.0%),归一化差值不透水面指数、归一化建筑指数和基于指数的建筑指数未能有效增强不透水面信息,提取精度较低(<75.0%)。此外,这8种不透水面指数都未能有效解决不透水面与大片裸地光谱混淆的问题,在裸地广泛分布的区域难以准确提取不透水面,平均提取精度仅为71.0%,影响了不透水面指数的大区域应用。

Utilizing Landsat TM Imagery to Map Greenhouses in Qingzhou, Shandong Province, China

To build a rapid and accurate method for greenhouse vegetable landinformation extraction using an index model derived from TM digital data of Qingzhou City, ShandongProvince, based on a systematic analysis of the spectral characteristics of different land use typesin the study area, a subset of the image was first made to eliminate the mountainous region notassociated with vegetable distribution, and then water body pixels were masked. With this the V_Iindex model for greenhouse vegetable land extraction was developed. The index model indicatedgreenhouse vegetable land for Qingzhou in April 2002 was concentrated in the southeast and aroundrural residential areas. Field data used for an accuracy evaluation showed that greenhouse hectaresdetermined with remote sensing were 95.9% accurate, and accuracy for the spatial distribution ofgreenhouse vegetable land cross checked with a random sample was 96.3%. Therefore, this approachprovided an effective method for greenhouse vegetable land information extraction and has potentialsignificance for management of greenhouse vegetable production in the study area, as well as NorthChina.

基于NPP-VIIRS夜间灯光数据和Landsat-8数据的城镇建筑用地提取方法改进——以广州市为例

以广州市为例,将Landsat-8-OLS数据与NPP-VIIRS夜间灯光数据相结合提取城镇建筑用地,在常规的NDBI指数、ULI指数方法的基础上进行改进,以获得更加精确的城镇建筑用地信息。首先,利用NPP-VIIRS夜间灯光数据得到城镇建筑用地的大致分布范围,基于Landsat-8-OLS数据提取NDBI、NDVI指数;然后通过分析夜间灯光建筑用地范围、NDVI指数,NDBI指数三者的特性,分别对三者图像进行二值化、求交运算来提取城镇建筑用地;最后将提取结果与传统的NDBI指数、ULI指数方法的提取结果进行对比,利用Google Earth高空间分辨率影像数据进行精度验证。结果表明,结合NPP-VIIRS数据和Landsat-8-OLS数据的多指数提取相交运算,可有效剔除提取结果中包含的裸土信息,与NDBI等指数方法相比,能得到更高的精度。

Land-Cover Classification and its Impact on Peshawar’s Land Surface Temperature Using Remote Sensing

Spatial and temporal informationon urban infrastructure is essential and requires various land-cover/land-use planning and management applications.Besides,a change in infrastructure has a direct impact on other land-cover and climatic conditions.This study assessed changes in the rate and spatial distribution of Peshawar district’s infrastructure and its effects on Land Surface Temperature(LST)during the years 1996 and 2019.For this purpose,firstly,satellite images of bands7 and 8 ETM+(Enhanced Thematic Mapper)plus and OLI(Operational Land Imager)of 30 m resolution were taken.Secondly,for classification and image processing,remote sensing(RS)applications ENVI(Environment for Visualising Images)and GIS(Geographic Information System)were used.Thirdly,for better visualization and more in-depth analysis of land sat images,pre-processing techniques were employed.For Land use and Land cover(LU/LC)four types of land cover areas were identified-vegetation area,water cover,urbanized area,and infertile land for the years under research.The composition of red,green,and near infra-red bands was used for supervised classification.Classified images were extracted for analyzing the relative infrastructure change.A comparative analysis for the classification of images is performed for SVM(Support Vector Machine)and ANN(Artificial Neural Network).Based on analyzing these images,the result shows the rise in the average temperature from 30.04℃ to 45.25℃.This only possible reason is the increase in the built-up area from 78.73 to 332.78 Area km^(2) from 1996 to 2019.It has also been witnessed that the city’s sides are hotter than the city’s center due to the barren land on the borders.

Comparative evaluation of modified neem leaf, neem leaf and woodash extracts on soil fertility improvement, growth and yields of maize (<i>Zea mays</i>L.) and watermelon (<i>Citrullus lanatus</i>) (Sole and Intercrop)

Two field experiments were carried out at Akure (7oN, 5o101E) in the rainforest zone of Nigeria in 2006 and 2007 to determine the effectiveness of neem leaf, woodash and modified neem leaf extracts as fertilizer sources in improving soil fertility, growth and yield of maize (Zea mays L) and watermelon (Citrulus lanatus) sole and intercrop. There were six treatments namely, poultry manure, neem leaf extract (sole), woodash extract, modified neem leaf (neem leaf + woodash), NPK 15-15-15 and a control (no fertilizer nor extract), replicated three times and arranged in a randomized complete block design (RCB). The extracts (neem leaf, wood ash and modified neem leaf) were applied at 1200 litres per hectare each, NPK 15-15-15 at 300 kg/ha and poultry was applied at 6t/ha. The results showed that there were significant increases (P 2O), K, Ca, Mg, Na, O.M, P and N compared to NPK 15-15-15 and neem leaf extract. For instance, modified neem leaf extract increased soil pH (H2O), K, Ca, Mg, Na, O.M, P and N by 12.4%, 32.8%, 25%, 23.7%, 19.32%, 17.24% and 20% respectively compared to neem leaf extract under intercrop plot. The high soil K/Ca, K/Mg and P/Mg ratios in the NPK 15-15-15 fertilizer treatment led to an imbalance in the supply of P, K, Ca and Mg nutrients to maize and watermelon crops. The least values for growth, yield and soil parameters were recorded under the control treatment. In these experiments, modified neem leaf extract (woodash + neem leaf extracts) applied at 1200 litres/ha was the most effective in improving soil fertility, growth and yield of maize and watermelon (sole and intercrop) and could substitute for 6 tons per hectare of poultry manure and 300kg/ha of NPK 15-15-15 fertilizer.

Dynamicity of Land Use/Land Cover(LULC):An analysis from peri-urban and rural neighbourhoods of Durgapur Municipal Corporation(DMC)in India

The availability of better economic possibilities and well-connected transportation networks has attracted people to migrate to peri-urban and rural neighbourhoods,changing the landscape of regions outside the city and fostering the growth of physical infrastructure.Using multi-temporal satellite images,the dynamics of Land Use/Land Cover(LULC)changes,the impact of urban growth on LULC changes,and regional environmental implications were investigated in the peri-urban and rural neighbourhoods of Durgapur Municipal Corporation in India.The study used different case studies to highlight the study area’s heterogeneity,as the phenomenon of change is not consistent.Landsat TM and OLI-TIRS satellite images in 1991,2001,2011,and 2021 were used to analyse the changes in LULC types.We used the relative deviation(RD),annual change intensity(ACI),uniform intensity(UI)to show the dynamicity of LULC types(agriculture land;built-up land;fallow land;vegetated land;mining area;and water bodies)during 1991-2021.This study also applied the Decision-Making Trial and Evaluation Laboratory(DEMATEL)to measure environmental sensitivity zones and find out the causes of LULC changes.According to LULC statistics,agriculture land,built-up land,and mining area increased by 51.7,95.46,and 24.79 km^(2),respectively,from 1991 to 2021.The results also suggested that built-up land and mining area had the greatest land surface temperature(LST),whereas water bodies and vegetated land showed the lowest LST.Moreover,this study looked at the relationships among LST,spectral indices(Normalized Differenced Built-up Index(NDBI),Normalized Difference Vegetation Index(NDVI),and Normalized Difference Water Index(NDWI)),and environmental sensitivity.The results showed that all of the spectral indices have the strongest association with LST,indicating that built-up land had a far stronger influence on the LST.The spectral indices indicated that the decreasing trends of vegetated land and water bodies were 4.26 and 0.43 km^(2)/a,respectively,during 1991-2021.In summary,this study can help the policy-makers to predict the increasing rate of temperature and the causes for the temperature increase with the rapid expansion of built-up land,thus making effective peri-urban planning decisions.

Impact of Urbanisation on Land Use/Land Cover in Puducherry City, India

The change of land use plays a major role in the developmental activity of a developing country. Due to rapid growth of urbanisation and dramatic increasing population, the fertile agricultural land has been converted to built-up area with respect to the demand for housing requirement and to the need for basic infrastructure facilities. The quantum of open space and surface water bodies has also been encroached. There has been a rapid growth of population in Puducherry city from 3.48 million in 1991 to 5.44 million in 2011. Hence the conservation of natural resources becomes one of the major challenges especially in small and medium town. This study was conducted to assess the effect of change on land use in urban agglomeration area of Puducherry city for the duration period from 1997 to 2017. There has been an increase in population in Puducherry city mainly attributed to higher scale of migration from adjoining rural areas and medium town for better education, job opportunities and quality life. Hence, it has been strongly recommended for stringent Development Control Regulations to quantify the urban sprawl and manage the impact of urbanisation of land use/land cover in Puducherry city.

基于landsat8序列影像的郑州市城市边缘带提取

城市边缘带是城市与乡村之间的过渡区域。我国城镇建设日益发展,使城市边缘带成为研究热点。以郑州市作为研究对象,利用RS和GIS技术,采用2013-2016年四景覆盖郑州市landsat8影像数据,选择基于土地利用程度的边缘带范围界定的方法,结合土地利用特征,设置阈值提取城市边缘带。结果显示城市边缘带呈环形,惠济区及经济开发区边缘带范围偏大,靠近山区的西南部边缘带范围偏小。对比得出2013年-2016年郑州市城市边缘带区域土地利用类型变化显著;建成区主要向北和西北部扩展,农村土地利用类型向城市建设用地过渡。

Forecast of Dynamic Change of Land Use Based on Cellular Automata

Land use change is a very complex process of evolution.On the basis of the principle of cellular automata,this article presents a kind of method that we can first mine state transition rule from historical map data,and then conduct forecast by virtue of Monte-Carlo method,achieving spatial dynamic forecast from map to map.We interpret TM remote sensing image in Ji'nan City in 2004 and 2006 to get present land use map for empirical research,and forecast land use map in 2012 and 2016,respectively.Studies show that this method of using spatial data to mine state transition rule,has advantages of simpleness,accuracy,strong real-time characteristic etc.in the simulation of dynamic change of land use,the results of which are roughly in line with the actual results,therefore,it can provide reference for land use planning.