More Like this

1. Impact of urban parameterization and integration of WUDAPT on the severe convection

   https://doi.org/10.1007/s43762-022-00071-w  

   Nadimpalli, Raghu; Patel, Pratiman; Mohanty, U. C.; Attri, S. D.; Niyogi, Dev (December 2022, Computational Urban Science)

   Abstract Amplified rates of urban convective systems pose a severe peril to the life and property of the inhabitants over urban regions, requiring a reliable urban weather forecasting system. However, the city scale's accurate rainfall forecast has constantly been a challenge, as they are significantly affected by land use/ land cover changes (LULCC). Therefore, an attempt has been made to improve the forecast of the severe convective event by employing the comprehensive urban LULC map using Local Climate Zone (LCZ) classification from the World Urban Database and Access Portal Tools (WUDAPT) over the tropical city of Bhubaneswar in the eastern coast of India. These LCZs denote specific land cover classes based on urban morphology characteristics. It can be used in the Advanced Research version of the Weather Research and Forecasting (ARW) model, which also encapsulates the Building Effect Parameterization (BEP) scheme. The BEP scheme considers the buildings' 3D structure and allows complex land–atmosphere interaction for an urban area. The temple city Bhubaneswar, the capital of eastern state Odisha, possesses significant rapid urbanization during the recent decade. The LCZs are generated at 500 m grids using supervised classification and are ingested into the ARW model. Two different LULC dataset, i.e., Moderate Resolution Imaging Spectroradiometer (MODIS) and WUDAPT derived LCZs and initial, and boundary conditions from NCEP GFS 6-h interval are used for two pre-monsoon severe convective events of the year 2016. The results from WUDAPT based LCZ have shown an improvement in spatial variability and reduction in overall BIAS over MODIS LULC experiments. The WUDAPT based LCZ map enhances high-resolution forecast from ARW by incorporating the details of building height, terrain roughness, and urban fraction. 

   more » « less
2. Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning

   https://doi.org/10.3390/s18113960  

   Castagno, Jeremy; Atkins, Ella (November 2018, Sensors)

   Geographic information systems (GIS) provide accurate maps of terrain, roads, waterways, and building footprints and heights. Aircraft, particularly small unmanned aircraft systems (UAS), can exploit this and additional information such as building roof structure to improve navigation accuracy and safely perform contingency landings particularly in urban regions. However, building roof structure is not fully provided in maps. This paper proposes a method to automatically label building roof shape from publicly available GIS data. Satellite imagery and airborne LiDAR data are processed and manually labeled to create a diverse annotated roof image dataset for small to large urban cities. Multiple convolutional neural network (CNN) architectures are trained and tested, with the best performing networks providing a condensed feature set for support vector machine and decision tree classifiers. Satellite image and LiDAR data fusion is shown to provide greater classification accuracy than using either data type alone. Model confidence thresholds are adjusted leading to significant increases in models precision. Networks trained from roof data in Witten, Germany and Manhattan (New York City) are evaluated on independent data from these cities and Ann Arbor, Michigan. 

   more » « less
3. Leveraging GANs for Synthetic Data Generation to Improve Intrusion Detection Systems

   https://doi.org/10.62411/faith.3048-3719-52  

   Rahman, Md Abdur; Francia, Guillermo A; Shahriar, Hossain (March 2025, Journal of Future Artificial Intelligence and Technologies)

   This research presents a hybrid intrusion detection approach that integrates Generative Adversarial Networks (GANs) for synthetic data generation with Random Forest (RF) as the primary classifier. The study aims to improve detection performance in cybersecurity applications by enhancing dataset diversity and addressing challenges in traditional models, particularly in detecting minority attack classes often underrepresented in real-world datasets. The proposed method employs GANs to generate synthetic attack samples that mimic real-world intrusions, which are then combined with real data from the UNSW-NB15 dataset to create a more balanced training set. By leveraging synthetic data augmentation, our approach mitigates issues related to class imbalance and enhances the generalization capability of the classifier. Extensive experiments demonstrate that RF trained on the combined dataset of real and synthetic data achieves superior detection performance compared to models trained exclusively on real data. Specifically, RF trained solely on the original dataset achieves an accuracy of 97.58%, whereas integrating GAN-generated synthetic data improves accuracy to 98.27%. The proposed methodology is further evaluated through comparative analysis against alternative classifiers, including Support Vector Machine (SVM), XGBoost, Gated Recurrent Unit (GRU), and related studies in the field. Our findings indicate that GAN-augmented training significantly enhances detection rates, particularly for rare attack types, while maintaining computational efficiency. Furthermore, RF outperforms other classifiers, including deep learning models, demonstrating its effectiveness as a lightweight yet robust classification method. Integrating GANs with RF offers a scalable and adaptable framework for intrusion detection, ensuring improved resilience against evolving cyber threats. 

   more » « less
4. Enhancing Global‐Scale Urban Land Cover Representation Using Local Climate Zones in the Community Earth System Model

   https://doi.org/10.1029/2025MS004934  

   Sun, Yuan; Oleson, Keith W; Zhao, Lei; Mills, Gerald; He, Cenlin; Demuzere, Matthias; Topping, David O; Zhang, Ning; Zheng, Zhonghua (November 2025, Journal of Advances in Modeling Earth Systems)

   Abstract Urban areas are increasingly vulnerable to the impacts of climate change, necessitating accurate simulations of urban climates in Earth system models (ESMs) in support of large‐scale urban climate adaptation efforts. ESMs underrepresent urban areas due to their small spatial extent and the lack of detailed urban landscape data. To enhance the accuracy of urban representation, this study integrated the local climate zones (LCZs) scheme within the Community Earth System Model (CESM) to better represent urban heterogeneity. We adopted a modular approach to incorporate the 10 built LCZ classes into CESM as a new option in addition to the default urban three‐class scheme (i.e., tall building district, high density, and medium density). CESM simulations using the LCZ‐based urban characteristics were validated globally at 20 flux tower sites, showing site‐averaged improvement in modeling upward longwave radiation () and anthropogenic heat flux (), but increased uncertainties in modeling sensible heat flux (). The root‐mean‐square error between the observed and simulated using the LCZ decreased by 4% compared to using the default. Model sensitivity experiments revealed that and had comparable sensitivity to LCZ urban morphological and thermal parameter subsets. This study assessed and demonstrated the implementation as the starting point for future work on better resolving urban areas in Earth system modeling. 

   more » « less
5. Studying the effect of a decision fusion model on enhanced hyperspectral images

   https://doi.org/10.1117/12.2560107  

   Theran, Carlos A.; Alvarez, Michael; Sierra, Heidy; Arzuaga, Emmanuel (May 2020, Proc. SPIE 11392, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXVI, 1139206)

   Messinger, David W.; Velez-Reyes, Miguel (Ed.)

   Recent advances in data fusion provide the capability to obtain enhanced hyperspectral data with high spatial and spectral information content, thus allowing for an improved classification accuracy. Although hyperspectral image classification is a highly investigated topic in remote sensing, each classification technique presents different advantages and disadvantages. For example; methods based on morphological filtering are particularly good at classifying human-made structures with basic geometrical spatial shape, like houses and buildings. On the other hand, methods based on spectral information tend to perform better classification in natural scenery with more shape diversity such as vegetation and soil areas. Even more, for those classes with mixed pixels, small training data or objects with similar re ectance values present a higher challenge to obtain high classification accuracy. Therefore, it is difficult to find just one technique that provides the highest accuracy of classification for every class present in an image. This work proposes a decision fusion approach aiming to increase classification accuracy of enhanced hyperspectral images by integrating the results of multiple classifiers. Our approach is performed in two-steps: 1) the use of machine learning algorithms such as Support Vector Machines (SVM), Deep Neural Networks (DNN) and Class-dependent Sparse Representation will generate initial classification data, then 2) the decision fusion scheme based on a Convolutional Neural Network (CNN) will integrate all the classification results into a unified classification rule. In particular, the CNN receives as input the different probabilities of pixel values from each implemented classifier, and using a softmax activation function, the final decision is estimated. We present results showing the performance of our method using different hyperspectral image datasets. 

   more » « less