Forest type identification by random forest classification combined with SPOT and multitemporal SAR data

We developed a forest type classification technology for the Daxing＇an Mountains of northeast China using multisource remote sensing data.A SPOT-5 image and two temporal images of RADARSAT-2 full-polarization SAR were used to identify forest types in the Pangu Forest Farm of the Daxing＇an Mountains.Forest types were identified using random forest（RF） classification with the following data combination types： SPOT-5 alone,SPOT-5 and SAR images in August or November,and SPOT-5 and two temporal SAR images.We identified many forest types using a combination of multitemporal SAR and SPOT-5 images,including Betula platyphylla,Larix gmelinii,Pinus sylvestris and Picea koraiensis forests.The accuracy of classification exceeded 88% and improved by 12% when compared to the classification results obtained using SPOT data alone.RF classification using a combination of multisource remote sensing data improved classification accuracy compared to that achieved using single-source remote sensing data.

Unsupervised Change Detection in Multitemporal SAR Images Using MRF Models

An unsupervised change-detection method that considers the spatial contextual information in a log-ratio difference image generated from multitemporal SAR images is proposed. A Markov random filed (MRF) model is particularly employed to exploit statistical spatial correlation of intensity levels among neighboring pixels. Under the assumption of the independency of pixels and mixed Gaussian distribution in the log-ratio difference image, a stochastic and iterative EM-MPM change-detection algorithm based on an MRF model is developed. The EM-MPM algorithm is based on a maximiser of posterior marginals (MPM) algorithm for image segmentation and an expectation-maximum (EM) algorithm for parameter estimation in a completely automatic way. The experiment results obtained on multitemporal ERS-2 SAR images show the effectiveness of the proposed method.

Remote Sensing Multitemporal Data for Geomorphological Analysis of the Murghab Alluvial Fan in Turkmenistan

Archaeological studies are ever more landscape-oriented, in order to study archaeological evidences in relation with their territorial contexts. In such a framework, reconstruction and understanding of ancient landscapes assume a crucial role for archaeological research. This study proposes a first morphological analysis of the whole Murghab alluvial fan in Turkmenistan, by means of the SRTM-DEM datum, and then the reconstruction of the ancient hydrography in the northeastern fringe of the fan, based on medium-high geometric resolution satellite data, and in continuity with previous studies. The importance to know historical fluvial network is due to the strict relationship between fresh water availability and human settlement distribution. SRTM-DEM, Corona, Soyouz KFA, Landsat, and Aster data were used, overlaying them in a GIS, and digitizing palaeochannels through photo-interpretation were done. Today, this is an almost desert area of the fan, and that is why it is easier to recognize buried forms by means of photo-interpretation, even though sometimes in a doubtful way. Despite the uncertainties, this model provided a useful tool for next and focused archaeological field surveys and excavations, aimed to find out human settlement evidences in correlation with ancient waterways.

Fine classification of rice paddy using multitemporal compact polarimetric SAR C band data based on machine learning methods

Rice is an important food crop for human beings.Accurately distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring,yield estimation,and phenological monitoring,which has significance for the development of modern agriculture.Compact polarimetric(CP)synthetic aperture radar(SAR)provides multichannel information and shows great potential for rice monitoring and mapping.Currently,the use of machine learning methods to build classification models is a controversial topic.In this paper,the advantages of CP SAR data,the powerful learning ability of machine learning,and the important factors of the rice growth cycle were taken into account to achieve high-precision and fine classification of rice paddies.First,CP SAR data were simulated by using the seven temporal RADARSAT-2 C-band data sets.Second,20-two CP SAR parameters were extracted from each of the seven temporal CP SAR data sets.In addition,we fully considered the change degree of CP SAR parameters on a time scale(ΔCP_(DoY)).Six machine learning methods were employed to carry out the fine classification of rice paddies.The results show that the classification methods of machine learning based on multitemporal CP SAR data can obtain better results in the fine classification of rice paddies by considering the parameters ofΔCP_(DoY).The overall accuracy is greater than 95.05%,and the Kappa coefficient is greater than 0.937.Among them,the random forest(RF)and support vector machine(SVM)achieve the best results,with an overall accuracy reaching 97.32%and 97.37%,respectively,and Kappa coefficient values reaching 0.965 and 0.966,respectively.For the two types of rice paddies,the average accuracy of the transplant hybrid(T-H)rice paddy is greater than 90.64%,and the highest accuracy is 95.95%.The average accuracy of direct-sown japonica(D-J)rice paddy is greater than 92.57%,and the highest accuracy is 96.13%.

Flood Duration Estimation Based on Multisensor,Multitemporal Remote Sensing:The Sardoba Reservoir Flood

Single-sensor monitoring of flood events at high spatial and temporal resolutions is difficult because of the lack of data owing to instrument defects,cloud contamination,imaging geometry.However,combining multisensor data provides an impressive solution to this problem.In this study,11 synthetic aperture radar(SAR)images and 13 optical images were collected from the Google Earth Engine(GEE)platform during the Sardoba Reservoir flood event to constitute a time series dataset.Threshold-based and indices-based methods were used for SAR and optical data,respectively,to extract the water extent.The final sequential flood water maps were obtained by fusing the results from multisensor time series imagery.Experiments show that,when compare with the Global Surface Water Dynamic(GSWD)dataset,the overall accuracy and Kappa coefficient of the water body extent extracted by our methods range from 98.8%to 99.1%and 0.839 to 0.900,respectively.The flooded extent and area increased sharply to a maximum between May 1 and May 4,and then experienced a sustained decline over time.The flood lasted for more than a month in the lowland areas in the north,indicating that the northern region is severely affected.Land cover changes could be detected using the temporal spectrum analysis,which indicated that detailed temporal information benefiting from the multisensor data is highly important for time series analyses.

Assessment of land use change and its effect on soil carbon stock using multitemporal satellite data in semiarid region of Rajasthan, India

Background:Land use change plays a vital role in global carbon dynamics.Understanding land use change impact on soil carbon stock is crucial for implementing land use management to increase carbon stock and reducing carbon emission.Therefore,the objective of our study was to determine land use change and to assess its effect on soil carbon stock in semi-arid part of Rajasthan,India.Landsat temporal satellite data of Pushkar valley region of Rajasthan acquired on 1993,2003,and 2014 were analyzed to assess land use change.Internal trading of land use was depicted throughmatrices.Soil organic carbon(SOC)stock was calculated for soil to a depth of 30 cm in each land use type in 2014 using field data collection.The SOC stock for previous years was estimated using stock change factor.The effect of land use change on SOC stock was determined by calculating change in SOC stock(t/ha)by deducting the base-year SOC stock from the final year stock of a particular land use conversion.Results:The total area under agricultural lands was increased by 32.14%while that under forest was decreased by 23.14%during the time period of 1993–2014.Overall land use change shows that in both the periods(1993–2003 and 2003–2014),7%of forest area was converted to agricultural land and about 15%changes occurred among agricultural land.In 1993–2003,changes among agricultural land led to maximum loss of soil carbon,i.e.,4.88 Mt C and during 2003–2014,conversion of forest to agricultural land led to loss in 3.16 Mt C.Conclusion:There was a continuous decrease in forest area and increase in cultivated area in each time period.Land use change led to alteration in carbon equity in soil due to change or loss in vegetation.Overall,we can conclude that the internal trading of land use area during the 10-year period(1993–2003)led to net loss of SOC stock by 8.29 Mt C.Similarly,land use change during 11-year period(2003–2014)caused net loss of SOC by 2.76 Mt C.Efforts should be made to implement proper land use management practices to enhance the SOC content.

Using Bayesian multitemporal classification to monitor tropical forest cover changes in Kalimantan,Indonesia

Significant areas of native forest in Kalimantan,on the island of Borneo,have been cleared for the expansion of plantations of oil palm and rubber.In this study multisource remote sensing was used to develop a time series of land cover maps that distinguish native forest from plantations.Using a study area in east Kalimantan,Landsat images were combined with either ALOS PALSAR or Sentinel-1 images to map four land cover classes(native forest,oil palm plantation,rubber plantation,non-forest).Bayesian multitemporal classification was applied to increase map accuracy and maps were validated using a confusion matrix;final map overall accuracy was>90%.Over 18 years from 2000 to 2018 nearly half the native forests in the study area were converted to either non-forest or plantations of either rubber or oil palm,with the highest losses between 2015 and 2016.Trending upwards from 2008 large areas of degraded or cleared forests,mapped as non-forest,were converted to oil palm plantation.Conversion of native forests to plantation mainly occurred in lowland and wetland forest,while significant forest regrowth was detected in degraded peatland.These maps will help Indonesia with strategies and policies for balancing economic growth and conservation.

Multi-temporal NDVI analysis using UAV images of tree crowns in a northern Mexican pine-oak forest

The use of unmanned aerial vehicles(UAV)for forest monitoring has grown significantly in recent years,providing information with high spatial resolution and temporal versatility.UAV with multispectral sensors allow the use of indexes such as the normalized difference vegetation index(NDVI),which determines the vigor,physiological stress and photo synthetic activity of vegetation.This study aimed to analyze the spectral responses and variations of NDVI in tree crowns,as well as their correlation with climatic factors over the course of one year.The study area encompassed a 1.6-ha site in Durango,Mexico,where Pinus cembroides,Pinus engelmannii,and Quercus grisea coexist.Multispectral images were acquired with UAV and information on meteorological variables was obtained from NASA/POWER database.An ANOVA explored possible differences in NDVI among the three species.Pearson correlation was performed to identify the linear relationship between NDVI and meteorological variables.Significant differences in NDVI values were found at the genus level(Pinus and Quercus),possibly related to the physiological features of the species and their phenology.Quercus grisea had the lowest NDVI values throughout the year which may be attributed to its sensitivity to relative humidity and temperatures.Although the use of UAV with a multispectral sensor for NDVI monitoring allowed genera differentiation,in more complex forest analyses hyperspectral and LiDAR sensors should be integrated,as well other vegetation indexes be considered.

Land Cover Classification and Forest Change Analysis, Using Satellite Imagery-A Case Study in Dehdez Area of Zagros Mountain in Iran

The importance of accurate and timely information describing the nature and extent of land resources and changes over time is increasing, especially in mountainous areas. We have developed a methodology to map and monitor land cover change using multitemporal Landsat Thematic Mapper (TM) and ASTER data in Zagros mountains of Iran for 1990, 1998, and 2006.Land-use/cover mapping is achieved through interpreta-tion of Landsat TM satellite images of 1990, 1998 and TERRA-ASTER image of 2006 using ENVI 4.3. Based on the Anderson land-use/cover classification system, the land-use and land-covers are classified as forest land, rangeland, water bodies, agricultural land and residential land. The unsupervised image classifi-cation method carried out prior to field visit, in order to determine strata for ground truth. Fieldwork carried out to collect data for training and validating land-use/cover interpretation from satellite image of 2006, and for qualitative description of the characteristics of each land-use/cover class. The land-use/cover maps of 1990, 1998 and 2006 were produced by using supervised image classification technique based on the Maxi-mum Likelihood Classifier (MLC) and 132 training samples. Error matrices as cross-tabulations of the mapped class vs. the reference class were used to assess classification accuracy. Overall accuracy, user’s and producer’s accuracies, and the Kappa statistic were then derived from the error matrices. A multi-date post-classification comparison change detection algorithm was used to determine changes in land cover in three intervals, 1990–1998, 1998–2006 and 1990–2006. To evaluate the change maps for the 1990 to 2006 interval, we randomly sampled the areas that classified as change and no-change and determined whether they were correctly classified. The maps showed that between 1990 and 2006 the amount of forest land de-creased from 67% to 38.5% of the total area, while rangelands, agriculture, settlement and surface water in-creased from 30.8% to 45%, 1.2% to 7.0%, 0.3% to 7.5% and 0.6% to 1.8%, respectively. The area was dominated by 35.9%, 28.9% and 29.3% dense forest, 42.2%, 46.4% and 43.2% open forest and 21.9%, 24.8% and 27.5% degraded forest in 1990, 1998 and 2006, respectively. During 16 years span period (1990-2006) about 10170.3 ha, 2963.4 ha, 351.7 ha and 3039.2 ha of forest lands were converted to range-land, agriculture, water body and settlement. The overall five-class classification accuracies averaged 78.6% for the three years. The overall accuracy of land cover change maps, generated from post-classification change detection methods and evaluated using several approaches, reached to 80.1%. The results quantify the land cover change patterns in the Zagrous highlands and demonstrate the potential of multitemporal Landsat and ASTER data to provide an accurate, economical means to map and analyze changes in land cover over time that can be used as inputs to land management and policy decisions.

Analysis of Urban Change in Shenzhen City Based on Landsat Archived Data

With the ongoing development of economy and urbanization in China, the change of land use types has attracted more and more attention. In this study we focused on the urban development of Shenzhen City, Guangdong Province, analyzing Landsat 5 TM and Landsat 8 OLI data. We used an SVM based classification, a land transfer matrix approach, a directional growth analysis method and we calculated the inversion of land surface temperature to derive information of land cover changes that occurred in the time period between 1987 and 2017. The results are combined with Shenzhen’s economy, transportation policy and other aspects to find the driving forces of the urban development. The results show that during the observed 30 years, the area of construction land has increased significantly. Most of it is converted from other lands, and some of them are reclaimed. Most rapidly developing are areas west and northwest of the Bao’an, Nanshan and Longhua. The vegetated areas decreased slightly. Caused by the continuous increase of the construction land, the so-called heat island effect emerges slightly but continuously.

Impact of Land Use/Land Cover Change on Surface Temperature Condition of Awka Town, Nigeria

This paper is aimed at identifying the land use/cover types in Awka in relation to their temporal dynamics, the extent of land use change in the city and effects of land use change on surface temperature. Multitemporal Landsat TM, ETM+ and OLI imageries were obtained at 15 years interval for 1986, 2000 and 2015 respectively. Image classification was conducted using supervised classification method. The result showed that built-up area has been on the increase, expanding from 9.55 sqkm in 1986 to 21.3 sqkm in 2000 and 21.45 sqkm in 2015. Cultivated lands have maintained a steady decline since 2000 having lost about 3.29 sqkm of its area. Similarly, vegetation, made up of dense, savanna and riparian, has been on a decline from a total of 33.69sqkm in 1986 to 21.407 sqkm losing about 12.29 sqkm of its area and increased by a mere 4.07 sqkm in 2015. These alterations had given rise to an average increase of 2.2°C in surface radiant temperature. This study recommends that relevant government planning agencies (ACTDA, ASHDC, etc.) should factor in the concept of greening and green spaces into their development policies and strategies to ensure that fair, conducive microclimate and sustainable environment is maintained in the Awka urban area.

Use of Sentinel-1 imagery for flood management in a reservoir-regulated river basin

Flood hazard monitoring and mapping is of great importance because it represents a significant contribution to risk management. The present study investigated the flood event that occurred downstream from the transboundary Strymon River basin, more specifically at Serres basin-a reservoir-regulated basin, in the beginning of 2015. The focus of this study was to better understand the spatio-temporal dynamic of the flood and the causes that initiated the hazard. Within the Serres basin, the Strymon transboundary river outflows to Lake Kerkini, which regulates water flow downstream for irrigation purposes and flood protection. For this research, a dataset of Sentinel-1 SAR GRD images was collected and processed covering the period of October 2014-October 2015 to investigate the water level changes in Lake Kerkini. Based on SAR images, binary water/non-water products and multitemporal RGB amplitude images were generated and interpreted. Sentinel-1 products have proved to be an effective tool on flood hazard dynamic extension mapping and estimation of water extent bodies retained by small reservoirs. In agreement with hydro-meteorological data and the high-resolution DEM, it was conceived that the flood event occurred due to the water volume flowing from upstream in the reservoir and the large amount of water draining from the tributaries into nearby sub-basins. Moreover, inefficient water management of the overwhelming water flow through the dam could further strengthen the flood event. The proposed approach, which is entirely based on open access remotely sensed data and processing tools, could be implemented in the same area for past flood events to produce archive retrospective data, as well as in other similar reservoir-regulated river basins in terms of water management and flood risk management.

Technique Based on Image Pyramid and Bayes Rule for Noise Reduction in Unsupervised Change Detection

In this paper,a technique based on image pyramid and Bayes rule for reducing noise effects in unsupervised change detection is proposed.By using Gaussian pyramid to process two multitemporal images respectively,two image pyramids are constructed.The difference pyramid images are obtained by point-by-point subtraction between the same level images of the two image pyramids.By resizing all difference pyramid images to the size of the original multitemporal image and then making product operator among them,a map being similar to the difference image is obtained.The difference image is generated by point-by-point subtraction between the two multitemporal images directly.At last,the Bayes rule is used to distinguish the changed pixels.Both synthetic and real data sets are used to evaluate the performance of the proposed technique.Experimental results show that the map from the proposed technique is more robust to noise than the difference image.

A volumetric change detection framework using UAV oblique photogrammetry–a case study of ultra-high-resolution monitoring of progressive building collapse

In this paper,we present a case study that performs an unmanned aerial vehicle(UAV)based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event.Multi-temporal oblique photogrammetry images are collected with 3D point clouds generated at different stages of the demolition.The geometric accuracy of the generated point clouds has been evaluated against both airborne and terrestrial LiDAR point clouds,achieving an average distance of 12 cm and 16 cm for roof and façade respectively.We propose a hierarchical volumetric change detection framework that unifies multi-temporal UAV images for pose estimation(free of ground control points),reconstruction,and a coarse-to-fine 3D density change analysis.This work has provided a solution capable of addressing change detection on full 3D time-series datasets where dramatic scene content changes are presented progressively.Our change detection results on the building demolition event have been evaluated against the manually marked ground-truth changes and have achieved an F-1 score varying from 0.78 to 0.92,with consistently high precision(0.92–0.99).Volumetric changes through the demolition progress are derived from change detection and have been shown to favorably reflect the qualitative and quantitative building demolition progression.