Text features in topographic maps are important for helping users to locate the area that a map covers and to understand the map's content. Previous works on the optical detection of map text from topographic maps have used geometric features, the Hough transform, and segmentation. However, these approaches still face challenges when detecting map text in complicated contexts, especially when the map text is touching other map features, such as contours or geographical features. Thus, state-of-the-art techniques for map text and feature recognition and manual interpretation and correction are always required to produce accurate results when optically converting topographic maps into a readable format. This paper proposes a methodological framework called the intelligent map reader that enables the automatic and accurate optical understanding of the content of a topographic map using deep learning techniques in combination with a gazetteer. The intelligent map reader framework includes the detection of map text via deep learning, the separation of text units via graph-based segmentation and clustering, optical character recognition (OCR) via an OCR engine, and digital-gazetteer-based map content understanding. Experimental results validate the efficiency and robustness of our proposed methodology for map text recognition and map content understanding. We expect the proposed intelligent map reader to contribute to various applications in the GeoAI field.

This article introduces our research in developing a probabilistic model to extract linear terrain features from high resolution Digital Elevation Models (DEMs). The proposed model takes full advantage of spatio-contextual information to characterize terrain changes. It first derives a quantifiable measure of spatio-contextual patterns of linear terrain features, such as ridgelines, valley lines and crater boundaries, and then adopts multiple neighborhood analysis and a probability model to address data uncertainty in terrain surface modeling. Different from traditional approaches, the proposed model has the ability to achieve near-automated processing. It also supports effective extraction of terrain features in both smooth and rough surfaces. Through a series of experiments, we demonstrate that the proposed approach outperforms existing techniques, including thresholding, stream/drainage network analysis, visual descriptor detection, object-based image analysis and edge detection. This work contributes to both the geospatial data science and geomorphology communities with a new way of utilizing high-resolution imagery in terrain analysis.

Building height is valuable for a variety of foci in urban studies. The traditional field investigations are not practical for the updates of massive building height in a large-scale urban area. Given the relationship between building structures and their shadow sizes, the building shadow becomes practical for estimating its corresponding building height when its geometrical shape is visible in newly emerging very-high-resolution (VHR) images. However, the shadow shape of different buildings might vary significantly, posing a great challenge to determining the edge of shadow useful for predicting building height. This study proposes a shadow pattern classification system ( ShadowClass ) to summarize the varied shadow shapes into a number of pattern categories and employ a cutting-edge CNN model to classify the extracted shadows into a pattern for automatically determining the edge of a building shadow being useful for building height estimation. We integrated the proposed approach into two branches of the state-of-the-art approaches: shadow-based building height estimation with open cyberinfrastructure and shadow-based building height estimation with VHR image. The experimental results proved that the proposed method could be a practical solution for single and isolated buildings that have their complete shadow shape.

With the development of remote sensing technology and computing science, remote sensing data present typical big data characteristics. The rapid development of remote sensing big data has brought a large number of data processing tasks, which bring huge challenges to computing. Distributed computing is the primary means to process remote sensing big data, and task scheduling plays a key role in this process. This study analyzes the characteristics of batch processing of remote sensing big data. This paper uses the Hungarian algorithm as a basis for proposing a novel strategy for task assignment optimization of remote sensing big data batch workflow, called optimal sequence dynamic assignment algorithm, which is applicable to heterogeneously distributed computing environments. This strategy has two core contents: the improved Hungarian algorithm model and the multi-level optimal assignment task queue mechanism. Moreover, the strategy solves the dependency, mismatch, and computational resource idleness problems in the optimal scheduling of remote sensing batch processing tasks. The proposed strategy likewise effectively improves data processing efficiency without increasing computer hardware resources and without optimizing the computational algorithm. We experimented with the aerosol optical depth retrieval algorithm workflow using this strategy. Compared with the processing before optimization, the makespan of the proposed method was shortened by at least 20%. Compared with popular scheduling algorithm, the proposed method has evident competitiveness in acceleration effect and large-scale task scheduling.

Near-surface NO ₂ (NS-NO ₂ ) is closely related to human health and the atmospheric environment. While top-down approaches have been widely applied to estimate NS-NO ₂ using satellite-based NO ₂ column measurements, there still exist significant defects, resulting in a low overall fit and significant amount of bias. This article combines GOME-2B and OMI satellite data to estimate daily NS-NO ₂ with a spatial resolution of 0.1° × 0.1° from 2014 to 2018 over Mainland China, using a machine learning method. The estimated result has four important characteristics. First, the sample-based cross validation with surface observations shows a good result with R ² = 0.80 and RMSE = 9.0 μ g/m ³ . Second, the underestimation in high concentration areas and overestimation in low concentration areas are both reduced, compared with the case of using OMI data alone. Third, the estimated NS-NO ₂ is consistent with surface observations in spatial distribution, and successfully represent both inter-annual changes and seasonal characteristics. Furthermore, the population-weighted NO ₂ -based estimated dataset shows a significant decline of pollution exposure levels from 2014 to 2018.