Multimodal Data and Multiscale Kernel-Based Multistream CNN for Fine Classification of a Complex Surface-Mined Area

Fine land cover classification (FLCC) of complex landscapes is a popular and challenging task in the remote sensing community. In complex surface-mined areas (CSMAs), researchers have conducted FLCC using traditional machine learning methods and deep learning algorithms. However, convolutional neural network (CNN) algorithms that may be useful for FLCC of CSMAs have not been fully investigated. This study proposes a multimodal remote sensing data and multiscale kernel-based multistream CNN (3M-CNN) model. Experiments based on two ZiYuan-3 (ZY-3) satellite imageries of different times and seasons were conducted in Wuhan, China. The 3M-CNN model had three main features: (1) multimodal data-based multistream CNNs, i.e., using ZY-3 imagery-derived true color, false color, and digital elevation model data to form three CNNs; (2) multisize neighbors, i.e., using different neighbors of optical and topographic data as inputs; and (3) multiscale convolution flows revised from an inception module for optical and topographic data. Results showed that the proposed 3M-CNN model achieved excellent overall accuracies on two different images, and outperformed other comparative models. In particular, the 3M-CNN model yielded obvious better visual performances. In general, the proposed process was beneficial for the FLCC of complex landscape areas.

WSN Deployment Strategy for Real 3D Terrain Coverage Based on Greedy Algorithm with DEM Probability Coverage Model

The key to the study of node deployment in Wireless Sensor Networks (WSN) is to find the appropriate location of the WSN nodes and reduce the cost of network deployment while meeting the monitoring requirements in the covered area. This paper proposes a WSN node deployment algorithm based on real 3D terrain, which provides an effective solution to the surface-covering problem. First of all, actual geographic elevation data is adopted to conduct surface modeling. The model can vividly reflect the real terrain characteristics of the area to be deployed and make the deployment plan more visible and easy to adjust. Secondly, a probabilistic coverage model based on DEM (Digital Elevation Model) data is proposed. Based on the traditional spherical coverage model, the influence of signal attenuation and terrain occlusion on the coverage model is added to make the deployment model closer to reality. Finally, the Greedy algorithm based on grid scanning is used to deploy nodes. Simulation results show that the proposed algorithm can effectively improve the coverage rate, reduce the deployment cost, and reduce the time and space complexity in solving the WSN node deployment problem under the complex 3D land surface model, which verifies the effectiveness of the proposed algorithm.

Flood susceptibility analysis of the Panjkora Valley Northern Pakistan, using frequencyratio approach

Purpose Floods are considered as one of the most lethal natural disasters having the potential to cause havoc to entire communities. Pakistan is the land of wide topographic and climatic variations which make it vulnerable to floods. The purpose of this paper is to identify flood susceptible zones in the Panjkora Basin using frequency ratio model. Design/methodology/approach A total of seven parameters or flood conditioning factors were considered, and weights were assigned according to the frequency ratio technique. For the preparation of layers, satellite imageries and digital elevation model data were used. Frequency ratio was calculated using correlation between these parameters and flood. Flood susceptibility index map was divided into five zones through quantile method in ArcMap. Findings Findings of the study reveal that near half of the area (43%) is located in the very high susceptible zone, while only 20% area is classified as low to very low susceptible. Originality/value This paper is entirely based on original research. The approach used in this study has not been applied to the study area before.

MORPHOMETRIC ANAYSIS OF THE MAJOR VALLEY SYSTEMS AROUND BENGALURU

The three major Valley systems of Bengaluru namely Vrishabhavathi Valley, Hebbal Valley and Kormangala-Challaghatta Valley houses many lakes and play a very important role in its hydrological processes. The morphometric analysis helps us to learn about the characteristics of the underlying rock type, pervious nature of soil, slope gradients, runoff behavior and water retention potential within the Valley systems. Morphometric analysis was carried out for Linear, areal and relief aspects. The Survey of India topographical maps and Digital Elevation Model data were used to prepare the base map and the drainage maps with the help of GIS software. The Strahler system of stream ranking was adopted. Among the three Valleys, Vrishabhavathi Valley is observed to be the largest Valley in terms of area and perimeter. Vrishabhavathi Valley basin has sixth order stream as the highest stream order where as the other two Valleys have fifth order stream as the highest order. The drainage pattern formed within the Valley systems was observed to be dendritic. The watershed shape factor showed that the Vrishabhavathi Valley is elongated in shape where as the K-C Valley and the Hebbal Valleys are less elongated in shape comparatively. The drainage density of the three Valleys revealed that they fall under coarse drainage density classification. The relief aspects of the three Valleys exhibit low reliefs indicating a flat surface. This helps in designing a sustainable management plan for the three major Valley systems in terms of their conservation and also ensure sustainable soil and water usage within the Valley systems.

Mapping Threats of Spring Frost Damage to Tea Plants Using Satellite-Based Minimum Temperature Estimation in China

Spring frost damage (SFD), defined as the disaster during the period of newly formed tea buds in spring caused by lower temperature and frost damage, is a particular challenge for tea plants (Camellia sinensis), whose capacity to adapt to extreme weather and climate impacts is limited. In this paper, the region of the Middle and Lower Reaches of the Yangtze River (MLRYR) in China was selected as the major tea plantation study area, and the study period was focused on the concentrated occurrence of SFD, i.e., from March to April. By employing the standard lapse rate of air temperature with elevation, a minimum temperature (Tmin) estimation model that had been previously established was used based on reconstructed MYD11A1 nighttime LST values for 3 × 3 pixel windows and digital elevation model data. Combined with satellite-based Tmin estimates and ground-based Tmin observations, the spatiotemporal characteristics of SFD for tea plants were systematically analyzed from 2003 to 2020 in the MLRYR. The SFD risks at three scales (temporal, spatial, and terrain) were then evaluated for tea plants over the MLRYR. The results show that both SFD days at the annual scale and SFD areas at the daily scale exhibited a decreasing trend at a rate of 2.7 days/decade and 2.45 × 104 ha/day, respectively (significant rates at the 0.05 and 0.01 levels, respectively). The period with the highest SFD risk appeared mainly in the first twenty days of March. However, more attention should be given to the mid-to-late April time period due to the occurrence of late SFD from time to time. Spatially, areas with relatively higher SFD days and SFD risks were predominantly concentrated in the higher altitude areas of northwestern parts of MLRYR for both multi-year averages and individual years. Fortunately, in regions with a higher risk of SFD, the distribution of tea plants was relatively scattered and the area was small. These findings will provide helpful guidance for all kinds of people, including government agencies, agricultural insurance agencies, and tea farmers, in order that reasonable and effective strategies to reduce losses caused by spring frost damage to tea plants may be recommended and implemented.

Assessing Potential Bioenergy Production on Urban Marginal Land in 20 Major Cities of China by the Use of Multi-View High-Resolution Remote Sensing Data

For the purpose of bioenergy production, biomass cropping on marginal land is an appropriate method. Less consideration has been given to estimating the marginal land in cities at a fine spatial resolution, especially in China. Marginal land within cities has great potential for bioenergy production. Therefore, in this research, the urban marginal land of 20 representative cities of China was estimated by using detailed land-cover and 3D building morphology information derived from Ziyuan-3 high-resolution remote sensing imagery, and ancillary geographical data, including land use, soil type, and digital elevation model data. We then classified the urban marginal land into “vacant land” and “land between buildings”, and further revealed its landscape patterns. Our results showed that: (1) the suitable marginal land area ranged from 17.78 ± 1.66 km2 to 353.48 ± 54.19 km2 among the 20 cities; (2) it was estimated that bioethanol production on marginal land could amount to 0.005–0.13 mT, corresponding to bioenergy of 2.1 × 1013–4.0 × 1014 J for one city; (3) from the landscape viewpoint, the marginal landscape pattern tended to be more fragmented in more developed cities. Our results will help urban planners to reclaim unused urban land and develop distributed bioenergy projects at the city scale.

An Emerging Fault Related Fold (Mahad Anticline) and its Morphotectonic Interpretations in Northern Iraq

In this study, morphotectonic analyses were prepared for an anticline existing to the north of Maqloub Anticline and extends toward north - south approximately, which is unfamiliar in relation to the major extension of the anticlines in the region. The study involves a structural interpretation of the anticline's origin and its relation with the faulting in the foreland zone in this area, specifically in foothill zone, because of the major fracture that is found adjacent and parallel to the axis of this anticline. The visual interpretation is the major tool used to determine the features of this anticline. Moreover, some facilitating remote sensing technologies, such as digital processing of satellite images and Digital Elevation Model data, were utilized to verify the shape of this geological feature. The origin of the fold was discussed through its relationship to the associated fault within the general tectonic framework and the surrounding areas. This study addresses the tectonic mechanism of the anticline as a fold-related fault mechanism. As a result, and through the compilation of the above interpretations, a final geological map was prepared for this anticline, along with a 3D model demonstrating its mechanism of folding. Proposed names were given to the anticline and the fault, which are Mahad Anticline and Mahad Fault , according to the name of their nearest town (Mahad Town).

A Low-Rank Group-Sparse Model for Eliminating Mixed Errors in Data for SRTM1

The elimination of mixed errors is a key preprocessing technology for the area of digital elevation model data analysis, which is important for further applying data. We associated group sparsity with the low-rank uniqueness of local transformations of mixing errors to effectively remove mixing errors in data from Shuttle Radar Topography Mission 1 (SRTM 1) based on the sparseness of low-rank groups. First, the stripe-error structure that appeared globally in multiple directions was able to be better represented locally using group-sparse regularization and the uniqueness of the data in the low-rank direction of the local range and using variational ideas to constrain the gradient direction of the data to avoid redundant elimination. Second, the nonlocal self-similarity of the weighted kernel norm was used to remove random noise. Finally, the proposed model for eliminating mixed errors was solved using an algorithm based on the multiplier method of alternating direction. Experiments using simulated and real data found that the proposed low-rank group-sparse method (LRGS) eliminated mixed errors in both visual and quantitative evaluations better than the most recent processing methods and existing dataset products.

Integration of Remotely Sensed Digital Elevation Model Data and Geographic Information System Facilities to Estimate Net Solar Radiation Variances in Iraq (1987-2017)

The calculation of potential earth's surface solar radiation is imperative for analyzing the atmosphere-vegetation-soil interaction process. Therefore, many schemes were introduced with direct (using net radiometer) or indirect (using air temperature or air plus soil temperatures) formulas. Three combinations of factors are known to control the Rn value; the astronomical based factors which determine the general spatial distribution of Rn values, the climatological factors which determine the assigned spatial variation of those values, and the topographical factors that influence climatological factors rates ( i.e. have indirect effects on Rn values). For Iraq, the ecosystem influences of global warming were obvious in the 1980s and the Rn rates approached peak values .. Thereafter, the general behavior of Rn rates was geographically-based , i.e. increasing rates in the middle and southern regions and descending rates in the northern parts, since it was spatially correlated in a reverse manner with RH values. In the present study, this issue was clarified by utilizing the standard annual mean Rn rate known for Iraq’s weather, which was 9.8MJ.m-2.year-1. The results showed that, in 1987, the area with annual mean Rn equal or higher than this annual standard rate was 305088.098 km2. The area was reduced to 241984.77 km2 in 1997, followed by an expansion to 294491.136 km2 in 2007, and another reduction to 277272.542 km2 in 2017.