International Journal of Digital Earth
ISSN / EISSN : 1753-8947 / 1753-8955
Published by: Informa UK Limited (10.1080)
Total articles ≅ 836
Latest articles in this journal
International Journal of Digital Earth pp 1-14; https://doi.org/10.1080/17538947.2021.1980125
With the advancement of satellite technology, a considerable amount of very high-resolution imagery has become available to be used for the Land Cover and Land Use (LCLU) classification task aiming to categorize remotely sensed images based on their semantic content. Recently, Deep Neural Networks (DNNs) have been widely used for different applications in the field of remote sensing and they have profound impacts; however, improvement of the generalizability and robustness of the DNNs needs to be progressed further to achieve higher accuracy for a variety of sensing geometries and categories. We address this problem by deploying three different Deep Neural Network Ensemble (DNNE) methods and creating a comparative analysis for the LCLU classification task. DNNE enables improvement of the performance of DNNs by ensuring the diversity of the models that are combined. Thus, enhances the generalizability of the models and produces more robust and generalizable outcomes for LCLU classification tasks. The experimental results on NWPU-RESISC45 and AID datasets demonstrate that utilizing the aggregated information from multiple DNNs leads to an increase in classification performance, achieves state-of-the-art, and promotes researchers to make use of DNNE.
International Journal of Digital Earth pp 1-15; https://doi.org/10.1080/17538947.2021.1980126
Various countries have rapidly implemented strict actions to slow the blowout of COVID-19. Many events were dis-regarded, and anthropogenic activities such as industrial and transport systems were at a stoppage. Many countries were on lockdown, including the largest emitters of carbon dioxide. Due to these lockdowns, anthropogenic activities have been reduced and reported that air quality improves at a regional scale in many countries, including India. Therefore, the current study using Greenhouse Gases Observing Satellite (GOSAT/IBUKI) datasets to monitor the fluctuation of the average global concentration of dry mole fractions of atmospheric Methane (CH4) and Carbon Dioxide (CO2) during these pandemic lockdowns from January to June 2020. Outputs emphasize no significant reduction in the average concentration of dry mole fractions of atmospheric CH4 over the globe, but a minor reduction was observed in global CO2 engagement. The average concentration of both gases compares at each ten-degree latitude. The study reveals that, against the regional breakdowns, these short time lockdowns are not enough to control the concentration of these greenhouse gases at a larger scale, such as 10˚ latitude and globally, except for a minor reduction in CO2 concentration.
International Journal of Digital Earth pp 1-14; https://doi.org/10.1080/17538947.2021.1970262
The study aims at developing an applicable methodology to produce the functional land-use map using only free and open-source data. Top-view Sentinel image and ground-view Open Street Map (OSM) data are chosen due to their extensive availability. The three-stage framework, including object-based image analysis, OSM data cleaning, and ontology-based decision fusion, is proposed and implemented with open-source tools. We applied the developed approach to districts 1, 4, and 7 of HoChiMinh city, representing the complexities of the dynamic change in big cities. The result showed a good functional land use map with 78.70% overall accuracy. The outcome presents the mismatch between the data-driven approach and human knowledge, which can be improved by ontology-based fusion with OSM data. The ontology-based framework comprises the common urban land-use classes and OSM attributes, which can be applied and extended in other urban areas. Additional text attributes may be applicable only locally and can be modified in our open-source framework. Object-based image analysis takes advantage of Google Earth Engine computing power, whereas ontology-based processing works well on a local computer. In future studies, adopted natural language processing to pre-process OSM data and ontology-based fusion will be implemented on the cloud-computing platform to enhance computational efficiency.
International Journal of Digital Earth pp 1-22; https://doi.org/10.1080/17538947.2021.1968047
Optical remote sensing allows to efficiently monitor forest ecosystems at regional and global scales. However, most of the widely used optical forward models and backward estimation methods are only suitable for forest canopies in flat areas. To evaluate the recent progress in forest remote sensing over complex terrain, a satellite-airborne-ground synchronous Fine scale Optical Remote sensing Experiment of mixed Stand over complex Terrain (FOREST) was conducted over a 1 km×1 km key experiment area (KEA) located in the Genhe Reserve Areain 2016. Twenty 30 m×30 m elementary sampling units (ESUs) were established to represent the spatiotemporal variations of the KEA. Structural and spectral parameters were simultaneously measured for each ESU. As a case study, we first built two 3D scenes of the KEA with individual-tree and voxel-based approaches, and then simulated the canopy reflectance using the LargE-Scale remote sensing data and image Simulation framework over heterogeneous 3D scenes (LESS). The correlation coefficient between the LESS-simulated reflectance and the airborne-measured reflectance reaches 0.68–0.73 in the red band and 0.56–0.59 in the near-infrared band, indicating a good quality of the experiment dataset. More validation studies of the related forward models and retrieval methods will be done.
International Journal of Digital Earth pp 1-23; https://doi.org/10.1080/17538947.2021.1968048
To find disaster relevant social media messages, current approaches utilize natural language processing methods or machine learning algorithms relying on text only, which have not been perfected due to the variability and uncertainty in the language used on social media and ignoring the geographic context of the messages when posted. Meanwhile, a disaster relevant social media message is highly sensitive to its posting location and time. However, limited studies exist to explore what spatial features and the extent of how temporal, and especially spatial features can aid text classification. This paper proposes a geographic context-aware text mining method to incorporate spatial and temporal information derived from social media and authoritative datasets, along with the text information, for classifying disaster relevant social media posts. This work designed and demonstrated how diverse types of spatial and temporal features can be derived from spatial data, and then used to enhance text mining. The deep learning-based method and commonly used machine learning algorithms, assessed the accuracy of the enhanced text-mining method. The performance results of different classification models generated by various combinations of textual, spatial, and temporal features indicate that additional spatial and temporal features help improve the overall accuracy of the classification.
International Journal of Digital Earth pp 1-15; https://doi.org/10.1080/17538947.2021.1966525
Fire, especially wildfire, which can be considered as one of the main threats to vegetation cover and animals' life, has attracted lots of attention from environmental researchers. To better manage the fire crisis and take the necessary measures to compensate for its damages, it is essential to have detailed information about the burn severity levels. Accordingly, satellite images and their spectral indices have been widely considered in the literature as powerful tools in producing burn severity information. Despite the efficiency of the previously proposed methods, the necessity of ground reference data for their thresholding step faces them with serious challenges. To address this problem, in this study, an automatic procedure based on the change-point analysis is presented for thresholding differenced normalized burn ratio (dNBR) and its another version, dNBR2. In this procedure, a mean-shift based change-point analysis is performed on the dNBR and dNBR2 images for classifying them into burn severity levels. Experiments, conducted on some parts of Alaska and California in the United States, illustrated the high efficiency of the proposed method. Moreover, as an applied experiment, the severity of the fires, occurred in 2020 in the Khaeiz protected area in Iran, was estimated and compared with local reports.
International Journal of Digital Earth pp 1-21; https://doi.org/10.1080/17538947.2021.1962996
Evapotranspiration is one of the most important elements of the hydrological cycle. Estimation of evapotranspiration is imperative for effective forest, irrigation, rangeland and water resources management as well as to increase yields and for better crop management. This study aims to evaluate the effectiveness of the Surface Energy Balance Algorithm for Land (SEBAL) in estimating evapotranspiration and crop coefficient of corn in the Mediterranean region of Adana province, Turkey. The Landsat 8 satellite images from March to September 2018 were used to acquire the coefficients of the respective bands. Then, the net radiation flux on the earth’s surface and the earth’s heat flux is obtained using incoming-outgoing radiation fluxes from albedo, surface emissivity coefficients, land surface temperature, and plant indicators. Next, the sensible heat flux is calculated by determining the hot and cold pixels under consideration via the atmospheric stability conditions. Finally, evapotranspiration maps are plotted. The crop coefficient of corn is also estimated with the respected maps being plotted. To validate the outcomes from the SEBAL algorithm, experimental methods were employed to calculate the evapotranspiration values and evaluated using suitable performance metrics. The results showed that the SEBAL generated evapotranspiration values are in high agreement with the FAO Penman-Monteith method registering the highest correlation (R = 0.91) and the lowest error (RMSE = 1.14). In addition, the SEBAL method registered the highest correlation values of 0.89, 0.87 and 0.68 with Turk, Makkink and Hargreaves experimental methods, respectively. Moreover, the crop coefficients estimated using SEBAL also manifested an acceptable correlation with all methods. The highest correlation value registered was with the FAO Penman-Monteith method (R = 0.98). The outcomes show that since the performance of the SEBAL algorithm in estimating the actual evapotranspiration and crop coefficient using Landsat 8 satellite images is acceptable, the SEBAL algorithm could be a very convenient method. Moreover, it could easily be assimilated into farming management systems and precision agriculture for better decision-making and higher yield.
International Journal of Digital Earth pp 1-31; https://doi.org/10.1080/17538947.2021.1966526
In this paper, time extension methods, originally designed for clear-sky land surface conditions, are used to estimate high-spatial resolution surface daily longwave (LW) radiation from the instantaneous Global LAnd Surface Satellite (GLASS) longwave radiation product. The performance of four time methods were first tested by using ground based flux measurements that were collected from 141 global sites. Combined with the accuracy of daily LW radiation estimated from the instantaneous GLASS LW radiation, the linear sine interpolation method performs better than the other methods and was employed to estimate the daily LW radiation as follows: The bias/Root Mean Square Error (RMSE) of the linear sine interpolation method were −6.30/15.10 W/m2 for the daily longwave upward radiation (LWUP), −1.65/27.63 W/m2 for the daily longwave downward radiation (LWDN), and 4.69/26.42 W/m2 for the daily net longwave radiation (LWNR). We found that the lengths of the diurnal cycle of LW radiation are longer than the durations between sunrise and sunset and we proposed increasing the day length by 1.5 h. The accuracies of daily LW radiation were improved after adjusting the day length. The bias/RMSE were −4.15/13.74 W/m2 for the daily LWUP, −1.3/27.52 W/m2 for the daily LWDN, and 2.85/25.91 W/m2 for the daily LWNR. We are producing long-term surface daily LW radiation values from the GLASS LW radiation product.
International Journal of Digital Earth pp 1-16; https://doi.org/10.1080/17538947.2021.1966527
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.
International Journal of Digital Earth pp 1-14; https://doi.org/10.1080/17538947.2021.1966524
Arctic sea ice and its snow cover are important components of the cryosphere and the climate system. A series of in situ snow measurements were conducted during the seventh Chinese Arctic expedition in summer 2016 in the western Arctic Ocean. In this study, we made an analysis of snow features on Arctic sea ice based on in situ observations and the satellite-derived parameter of snow grain size from MODIS spectral reflectance data. Results indicate that snow depth on Arctic sea ice varied between 19 and 241 mm, with a mean value of 100 mm. The mean density of the snow was 340.4 kg/m3 during the expedition, which was higher than that reported in previous literature. The measurements revealed that a depth hoar layer was widely developed in the snow, accounting for 30%∼50% of the total snow depth. The equivalent snow grain size was small on the surface and large at the bottom in snow pits. The average relative error between MODIS-derived snow grain size and in situ measured surface snow grain size is 14.6%, indicating that remote sensing is a promising method to obtain large-scale information of snow grain size on Arctic sea ice.