Shallow water bathymetry based on a back propagation neural network and ensemble learning using multispectral satellite imagery

The back propagation(BP)neural network method is widely used in bathymetry based on multispectral satellite imagery.However,the classical BP neural network method faces a potential problem because it easily falls into a local minimum,leading to model training failure.This study confirmed that the local minimum problem of the BP neural network method exists in the bathymetry field and cannot be ignored.Furthermore,to solve the local minimum problem of the BP neural network method,a bathymetry method based on a BP neural network and ensemble learning(BPEL)is proposed.First,the remote sensing imagery and training sample were used as input datasets,and the BP method was used as the base learner to produce multiple water depth inversion results.Then,a new ensemble strategy,namely the minimum outlying degree method,was proposed and used to integrate the water depth inversion results.Finally,an ensemble bathymetric map was acquired.Anda Reef,northeastern Jiuzhang Atoll,and Pingtan coastal zone were selected as test cases to validate the proposed method.Compared with the BP neural network method,the root-mean-square error and the average relative error of the BPEL method can reduce by 0.65–2.84 m and 16%–46%in the three test cases at most.The results showed that the proposed BPEL method could solve the local minimum problem of the BP neural network method and obtain highly robust and accurate bathymetric maps.

Pinpointing Source of Mekong and Measuring Its Length Through Analysis of Satellite Imagery and Field Investigations

For centuries, explorers and scientists from different countries had made their own conclusions on the source of the Mekong. However, the geographic source of the Mekong is still arguable because of the complexity of the Mekong source water system, inaccessible environment and the varied technologies used by those explorers and scientists. The satellite remote sensing technology has been used to pinpoint the source of the Mekong, associated with the on-the-spot investigations made by the authors in June 1999 and September 2002. The actual length of the Mekong has also been calculated.

Arbitrary Scale Super Resolution Network for Satellite Imagery

Recently,satellite imagery has been widely applied in many areas.However,due to the limitations of hardware equipment and transmission bandwidth,the images received on the ground have low resolution and weak texture.In addition,since ground terminals have various resolutions and real-time playing requirements,it is essential to achieve arbitrary scale super-resolution(SR)of satellite images.In this paper,we propose an arbitrary scale SR network for satellite image reconstruction.First,we propose an arbitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbitrary scale enlarged SR outputs.Second,we design an edge reinforcement module to enhance the highfrequency details in satellite images through a twobranch network.Finally,extensive upsample experiments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counterparts.

On RPC Model of Satellite Imagery

The RPC model has recently raised considerable interest in the photogrammetry and remote sensing community. The RPC is a generalized sensor model that is capable of achieving high approximation accuracy. Unfortunately, the computation of the parameters of RPC model is subject to the initial of the parameter in all available literature. An algorithm for computation of parameters of RPC model without initial value is presented and tested on SPOT-5, CBERS-2, ERSq imageries. RPC model is suitable for both push-broom and SAR imagery.

Change Detection of Lake Chad Water Surface Area Using Remote Sensing and Satellite Imagery

The Lake Chad located in the west-central Africa in the Sahel region at the edge of the Sahara experienced severe drought during 1970s and 1980s and overexploitation (unintegrated and unsustainable use), which is a result of variant land uses and water management practices during the last 50 years. This resulted in a decline of the water level in the Lake and surrounding rivers. The present study analyzed satellite images of Lake Chad from Landsat-MSS, Landsat-OLI to investigate the change of the open water surface area during the years of 1973, 1987, 2001, 2013, and 2017. Supervised classifications were performed for the land cover analysis. The open water area in 1973 was covering 16,157.34 km2 approximately, and that was 64.6% of the total lake area in the 1960s. As an ultimate result of the extreme drought that the study area witnessed through 1970s-1980s, the open water area has decreased to 1831.44 km2, i.e. around 11.33%, compared to that in 1973. The dilemma that the study area is suffering from is believed to be a catastrophic complication of the aforementioned drought crisis, which arose as an ultimate result the climate change, global warming, and the unintegrated and unsustainable use of water challenges the study area is still encountering.

Identification of climatic and environmental factors associated with incidence of cutaneous leishmaniasis in Central Iran using satellite imagery

Objective:To determine the effect of climatic and environmental factors on the incidence of cutaneous leishmaniasis in Qom province in 2018.Methods:In this cross-sectional study,the data on cutaneous leishmaniasis incidence were collected from the Disease Control and Prevention Center in Qom province.Climatic and environmental data including Normalized Difference Vegetation Index(NDVI),Land Surface Temperature(LST),and soil moisture were extracted using satellite images.Data of altitude and sunny hours were provided based on shuttle radar topography mission digital elevation model and hemispherical viewshed algorithm,respectively.The associations of climatic and environmental variables with the incidence of the disease were analyzed by Pearson correlation method.The Arc GIS 10.3 software was used to determine the geographical distribution of these factors.Results:There were positive correlations between cutaneous leishmaniasis incidence and the two climatic factors:LST and sunny hours per day(P=0.041,P=0.016),and it had weak negative correlations with the digital elevation model(P=0.27),soil moisture(P=0.54),and NDVI(P=0.62).The time delay analysis showed that in one-,two-,and three month periods,the correlations increased with a 95%confidence interval.Accordingly,the correlation with the three-month time delay was positive and relatively strong between the cutaneous leishmaniasis incidence and LST and sunny hours(P=0.027,P=0.02);nevertheless,there were negative correlations between the cutaneous leishmaniasis incidence and the soil moisture(P=0.27)and NDVI(P=0.62).Conclusions:As Qom is located in one of the semi-arid climate zones,topography and solar energy are important factors affecting the incidence of cutaneous leishmaniasis in autumn.Therefore,appropriate disease control programs are recommended.

Spatio-Temporal Analysis of Landuse/Landcover Change of District Pishin Using Satellite Imagery and GIS

Detecting change on the face of the globe using GIS (Geographic Information System) aided by remotely sensed imagery is now becoming an indispensable tool in managing the resources of our planet. The present study with the help of GIS and remote sensing (RS) is also a similar attempt in recording and quantifying change in land use and land cover in district Pishin both in spatial and temporal extents. Satellite imagery was acquired from the USGS official website from three LANDSAT satellites. Theses satellites are LANDSAT 5, LANDSAT7 and LANDSAT 8. The data were acquired for the years 1992, 2003 and 2013. Satellite imagery was processed in ArcMap 10.1 and maximum likelihood supervised image classification was applied in reaching the goal of detecting change. The result of the analysis revealed that built-up area was increased by 5.84%;vegetation was increased by 3.89%;water bodies were increased by 0.05% and bare surfaces were decreased by 9.78%. The decrease in the barren surfaces was attributed to the increase in vegetation and built-up area which replaced the barren land in the study area. This paper also shows the significance and potential of digital change detection methods in managing the resources of our environment and keeping an eye on the land use and land cover of our Earth.

ANALYSIS OF AMBIENT FIELDS AND SATELLITE IMAGERY CHARACTERISTICS OF EFFECT OF BAY OF BENGAL STORMS ON LOW- LATITUDE PLATEAU

Based on the composite analysis method, 12 rainstorms triggered by Bay of Bengal storms (shortened as B-storms hereafter) across the whole province of Yunnan were studied, and some interesting results of rain and circulation characteristics influenced by the storms were obtained for low-latitude plateau. Usually, when a rainstorm weather occurs in low-latitude plateau, the B-storm center locates in the central, east or north parts of the Bay of Bengal. At the same time, the subtropical high ridge moves to 15°N– 20°N and the west ridge point moves to the Indo-china Peninsula from the South China Sea and the low-latitude plateau is controlled by southwest air streams coming from the front of the trough and the periphery of the subtropical high. The southwest low-level jet stream from the east side of the bay storm has great effect on heavy rains. On the one hand, the southwest low-level jet stream is playing the role of transporting water vapor and energy. On the other hand, the southwest low-level jet stream is helpful to keep essential dynamical condition. From the analysis of the satellite cloud imagery, it is found that mesoscale convection cloud clusters will keep growing and moving into the low-latitude plateau to cause heavy rains when a storm forms in the Bay of Bengal.

Enhancing Tropical Cyclone Intensity Estimation from Satellite Imagery through Deep Learning Techniques

This study first utilizes four well-performing pre-trained convolutional neural networks(CNNs) to gauge the intensity of tropical cyclones(TCs) using geostationary satellite infrared(IR) imagery.The models are trained and tested on TC cases spanning from 2004 to 2022 over the western North Pacific Ocean.To enhance the models performance,various techniques are employed,including fine-tuning the original CNN models,introducing rotation augmentation to the initial dataset,temporal enhancement via sequential imagery,integrating auxiliary physical information,and adjusting hyperparameters.An optimized CNN model,i.e.,visual geometry group network(VGGNet),for TC intensity estimation is ultimately obtained.When applied to the test data,the model achieves a relatively low mean absolute error(MAE) of 4.05 m s~(-1).To improve the interpretability of the model,the SmoothGrad combined with the Integrated Gradients approach is employed.The analyses reveal that the VGGNet model places significant emphasis on the distinct inner core region of a TC when estimating its intensity.Additionally,it partly takes into account the configuration of cloud systems as input features for the model,aligning well with meteorological principles.The several improvements made to this model's performance offer valuable insights for enhancing TC intensity forecasts through deep learning.

Mapping common and glossy buckthorns (Frangula alnus and Rhamnus cathartica) using multi-date satellite imagery WorldView-3, GeoEye-1 and SPOT-7

Buckthorns(Glossy buckthorn,Frangula alnus and common buckthorn,Rhamnus cathartica)represent a threat to biodiversity.Their high competitivity lead to the replacement of native species and the inhibition of forest regeneration.Early detection strategies are therefore necessary to limit invasive alien plant species’impacts,and remote sensing is one of the techniques for early invasion detection.Few studies have used phenological remote sensing approaches to map buckthorn distribution from medium spatial resolution images.Those studies highlighted the difficulty of detecting buckthorns in low densities and in understory using this category of images.The main objective of this study was to develop an approach using multi-date very high spatial resolution satellite imagery to map buckthorns in low densities and in the understory in the Québec city area.Three machine learning classifiers(Support Vector Machines,Random Forest and Extreme Gradient Boosting)were applied to WorldView-3,GeoEye-1 and SPOT-7 satellite imagery.The Random Forest classifier performed well(Kappa=0.72).The SVM and XGBoost’s coefficient Kappa were 0.69 and 0.66,respectively.However,buckthorn distribution in understory was identified as the main limit to this approach,and LiDAR data could be used to improve buckthorn mapping in similar environments.

IMPROVED MAN-COMPUTER INTERACTIVE CLASSIFICATION OF CLOUDS BASED ON BISPECTRAL SATELLITE IMAGERY

In this paper,improvement on man-computer interactive classification of clouds based on hispeetral satellite imagery has been synthesized by using the maximum likelihood automatic clustering(MLAC)and the unit feature space classification(UFSC)approaches.The improved classification not only shortens the time of sample-training in UFSC method,but also eliminates the inevitable shortcomings of the MLAC method.(e.g.,1.sample selecting and training is confined only to one cloud image:2.the result of clustering is pretty sensitive to the selection of initial cluster center:3.the actual classification basically can not satisfy the supposition of normal distribution required by MLAC method;4.errors in classification are difficult to be modified.) Moreover,it makes full use of the professionals'accumulated knowledge and experience of visual cloud classifications and the cloud report of ground observation,having ensured both the higher accuracy of classification and its wide application as well.

A combined image matching method for Chinese optical satellite imagery

Image matching is one of the key technologies for digital Earth.This paper presents a combined image matching method for Chinese satellite images.This method includes the following four steps:(1)a modified Wallis-type filter is proposed to determine parameters adaptively while avoiding over-enhancement;(2)a mismatch detection procedure based on a global-local strategy is introduced to remove outliers generated by the Scale-invariant feature transform algorithm,and geometric orientation with bundle block adjustment is employed to compensate for the systematic errors of the position and attitude observations;(3)we design a novel similarity measure(distance,angle and the Normalized Cross-Correlation similarities,DANCC)which considers geometric similarity and textural similarity;and(4)we introduce a hierarchical matching strategy to refine the matching result level by level.Four typical image pairs acquired from Mapping Satellite-1,ZY-102C,ZY-3 and GeoEye-1,respectively,are used for experimental analysis.A comparison with the two current main matching algorithms for satellite imagery confirms that the proposed method is capable of producing reliable and accurate matching results on different terrains from not only Chinese satellite images,but also foreign satellite images.

Computer Identification of Multispectral Satellite Cloud Imagery

A dynamic clustering method based on multispectral satellite imagery to identify the different features is described. The channel combinations selected are for the different purposes in classification. Several cases are presented using the polar-orbiting satellite imageries.

New Progress in the Application of Satellite Thermal Infrared Imagery to Earthquake Prediction

The concept of stochastic resonance (SR) has been introduced into the analysis of satellite thermal infrared images. Six kinds of anomalous phenomena related to crustal movement were recognized in satellite thermal infrared images. Six diagnostic indicators for the prediction of global earthquakes with magnitude ≥6.0 and their quantitative evaluation standards have been established. The microscopic behavior of global crustal movement is successfully controlled by using satellite thermal infrared imagery, and the occurrence time and magnitude of over 80% of global strong earthquakes occurred since the foundation of the observation station have been successfully predicted. It is believed that the combination of satellite thermal infrared information with macroscopic anomalous phenomena will play an important role in earthquake hazard reduction.

Characteristics of an Explosive Cyclone over Northeast China Revealed by Satellite Water Vapor Imagery

In this paper,an explosive cyclone(EC)that occurred over Northeast China in the spring of 2016 is studied by using 6.7μm FY satellite water vapor(WV)imagery and NCEP(1°×1°)reanalysis data.Moreover,the evolutions of the upper-level jet stream(ULJ),the vertical motions,and the potential vorticity(PV)are analyzed in detail.Results show that different shapes of the WV image dark zones could reflect different stages of the EC.At the pre-explosion stage,a small dark zone and an S-shaped baroclinic leaf cloud can be found on the WV imagery.Then the dark zone expands and the leaf cloud grows into a comma-shaped cloud at the explosively developing stage.At the post-explosion stage,the dark zone brightens,and the spiral cloud forms.The whole process can be well described by the WV imagery.The dynamic dry band associated with the sinking motion and the ULJ can develop into the dry intrusion later,which is an important signal in forecasting the EC and should be paid attention to when analyzing the WV imagery.Furthermore,the mechanism is also analyzed in detail in this article.EC usually occurs in the left-exit region of the 200-h Pa jet and the region ahead of the 500-h Pa trough where there is significant positive vorticity advection(PVA).When the EC moves onto the sea surface,the decreased friction would favour the development of the EC.The upper-level PVA,the strong convergence at low level,and the divergence at high levels can maintain the strong updraft.Meanwhile,the high PV zone from the upper levels extends downward,approaching the cyclone.Together,they keep the cyclone deepening continuously.

Imagery Data Quality of ZY Satellite Reached International Level

The in-orbit commissioning of ZY-1 02C satellite is proceeding smoothly. According to the relevant experts in this field, the imagery quality of the satellite has reached or nearly reached the level of international satellites of the same kind. ZY-1 02C satellite and ZY-3 satellite were successfully launched on December 22, 2011 and January 9, 2012 respectively. China Centre for Resources Satellite Data andApplication (CRSDA) was responsible for the building of a ground

Mapping Air Quality Using Remote Sensing Technology: A Case Study of Nairobi County

Nairobi County experiences rapid industrialization and urbanization that contributes to the deteriorating state of air quality, posing a potential health risk to its growing population. Currently, in Nairobi County, most air quality monitoring stations use low-cost, inaccurate monitors prone to defects. The study’s objective was to map Nairobi County’s air quality using freely available remotely sensed imagery. The Air Pollution Index (API) formula was used to characterize the air quality from cloud-free Landsat satellite images i.e., Landsat 5 TM, Landsat 7 ETM+, and Landsat 8 OLI from Google Earth Engine. The API values were computed based on vegetation indices namely NDVI, TVI, DVI, and the SWIR1 and NIR bands on the QGIS platform. Qualitative accuracy assessment was done using sample points drawn from residential, industrial, green spaces, and traffic hotspot categories, based on a passive-random sampling technique. In this study, Landsat 5 API imagery for 2010 provided a reliable representation of local conditions but indicated significant pollution in green spaces, with recorded values ranging from -143 to 334. The study found that Landsat 7 API imagery in 2002 showed expected results with the range of values being -55 to 287, while Landsat 8 indicated high pollution levels in Nairobi. The results emphasized the importance of air quality factors in API calibration and the unmatched spatial coverage of satellite observations over ground-based monitoring techniques. The study recommends the recalibration of the API formula for characteristic regions, exploring newer satellite sensors like those onboard Landsat 9 and Sentinel 2, and involving key stakeholders in a discourse to develop a suitable Kenyan air quality index.

Investigation on the Relationship between Population Density and Satellite Image Features——a Deep Learning Based Approach

Timely and accurate population statistic data plays an important role in many fields.To illustrate the demographic characteristics,population density is a crucial factor in evaluating population data.With a dynamic regional migration in population,it is a challenging job to evaluate population density without a census-based survey.We present the approach to classify satellite images in different magnitudes in population density and execute the comparative experiment to discuss the factors that influence the identification to the images with the deep learning approach.In this paper,we use satellite imagery and community population density data.With convolutional neural networks,we evaluated the performance of CNN on population estimation with satellite images,found the features that are important in population estimation,and then perform the sensitive analysis.

Retrieval of High Resolution Satellite Images Using Texture Features

In this research, a content-based image retrieval （CBIR） system for high resolution satellite images has been developed by using texture features. The proposed approach uses the local binary pattern （LBP） texture feature and a block based scheme. The query and database images are divided into equally sized blocks, from which LBP histograms are extracted. The block histograms are then compared by using the Chi-square distance. Experimental results show that the LBP representation provides a powerful tool for high resolution satellite images （HRSI） retrieval.

Overcast sky condition prevails on and influences the biometeorology of the tropical Andean Páramos

Clouds play a major role in modulating the biometeorological processes. We studied the influence of cloudiness on four biometeorological variables:daily air temperature(Tair), relative humidity(RH),reference evapotranspiration(ETr),and photosynthetic active radiation(PAR), recorded at four sites of Andean Páramos in southern Ecuador during 2.5 to 5.5 years. First, we quantified both the cloud cover percentage(Cloud%) creating cloud masks over the visible bands of Landsat 7 images and the sky condition(K_(T)) using the records of solar and extraterrestrial radiation. Second, we estimated KTfrom Cloud%. Finally, we quantified T_(air), RH, ET_(r), and PAR under clear, cloudy, and overcast K_(T) and their dependence on KT. The average Cloud% ranged between 65%–76%, and KTcorroborated the prevailing overcast sky(between 55% and 72.5% of the days) over the páramos. The proposed model performed well in the sites of calibration(R^(2)= 0.80;MBE = 0.00;RMSE = 0.05) and validation(R^(2)= 0.74;MBE =-0.07;RMSE = 0.11). The overcast sky diminished T_(air)(≤ 10℃), ET_(r)(≤ 1.6 mm day-1), and PAR(4 MJ m^(-2)day^(-1)) and increased RH(≥ 88%),while the variables showed the opposite behavior during the uncommon clear sky(≤ 5.5% of the days).Thus, mostly the dynamic of RH(R^(2)≥ 0.62), ETr(R^(2)≥ 0.85), and PAR(R2≥ 0.77) depended on K_(T). Hence,the prevailing overcast sky influenced the biometeorology of the páramos.