Urban Catchment-Scale Blue-Green-Gray Infrastructure Classification with Unmanned Aerial Vehicle Images and Machine Learning Algorithms

Abstract

Green infrastructure (GI), such as green roofs, is now widely used in sustainable urban development. An accurate mapping of GI is important to provide surface parameterization for model development. However, the accuracy and precision of mapping GI is still a challenge in identifying GI at the small catchment scale. We proposed a framework for blue-green-gray infrastructure classification using machine learning algorithms and unmanned aerial vehicle (UAV) images that contained digital surface model (DSM) information. We used the campus of the Southern University of Science and Technology in Shenzhen, China, as a study case for our classification method. The UAV was a DJI Phantom 4 Multispectral, which measures the blue, green, red, red-edge, and near-infrared bands and DSM information. Six machine learning algorithms, i.e., fuzzy classifier, k-nearest neighbor classifier, Bayes classifier, classification and regression tree, support vector machine (SVM), and random forest (RF), were used to classify blue (including water), green (including green roofs, grass, trees (shrubs), bare land), and gray (including buildings, roads) infrastructure. The highest kappa coefficient was observed for RF and the lowest was observed for SVM, with coefficients of 0.807 and 0.381, respectively. We optimized the sampling method based on a chessboard grid and got the optimal sampling interval of 11.6 m to increase the classification efficiency. We also analyzed the effects of weather conditions, seasons, and different image layers, and found that images in overcast days or winter days could improve the classification accuracy. In particular, the DSM layer was crucial for distinguishing green roofs and grass, and buildings and roads. Our study demonstrates the feasibility of using UAV images in urban blue-green-gray infrastructure classification, and our infrastructure classification framework based on machine learning algorithms is effective. Our results could provide the basis for the future urban stormwater management model development and aid sustainable urban planning.

A multi-strategy-mode waterlogging-prediction framework for urban flood depth

“…Characteristics of the methods need to be clarified with respect to the type and number of available training data and the type of prediction task, e.g., water level and streamflow. Jia et al (2022) classified urban catchment areas to realize the waterlogging risk prediction based on unmanned aerial vehicle images and machine learning algorithms. Puttinaovarat and Horkaew (2020) proposed a novel flood forecasting system based on fusing meteorological, hydrological, geospatial, and crowdsourced big data in an adaptive machine learning framework.…”

A Multi-strategy-mode-waterlogging-prediction Framework for Urban Flood Depth

“…J. Jia et al classified urban catchment areas based on unmanned aerial vehicle images and machine learning algorithms (Jia et al, 2022). Supattra Puttinaovarat proposed a novel flood forecasting system based on fusing meteorological, hydrological, geospatial, and crowdsource big data in an adaptive machine learning framework (Puttinaovarat & Horkaew, 2020).…”

Emprego de classificação orientada a objeto para atualização de área de imóveis urbanos no recadastramento imobiliário

“…Em [Trevisiol et al 2021] os autores obtiveram 94% de acurácia global na identificac ¸ão de construc ¸ões na cidade de Bologna, Itália, utilizando GEOBIA (eCognition®) e imagem de alta resoluc ¸ão espacial. De forma análoga, os autores [Jia et al 2022] utilizaram imagem de VANT e GEOBIA (eCognition®) para classificar diferentes usos no campus de uma universidade chinesa. Os classificadores testados foram fuzzy, k-Nearest Neighbors (KNN), Bayes, SVM e RF, sendo este último o que apresentou a melhor acurácia global (84,9%).…”

“…O uso de redes convolucionais (aprendizado profundo) aparece como uma tendência na detecc ¸ão de construc ¸ões urbanas. Outras aplicac ¸ões comuns envolvendo classificac ¸ão automática de telhados ocorrem na identificac ¸ão de locais adequados para instalac ¸ão de painéis solares e também dos chamados telhados verdes [Jia et al 2022, Shao et al 2021].…”

“…A classificac ¸ão automática de imagens apresenta-se como uma alternativa à vetorizac ¸ão manual. Por isso, diversos autores têm aplicado essa técnica para identificar coberturas em área urbana (telhados) [Chen et al 2018, Kim et al 2011, Jia et al 2022, Pilinja Subrahmanya et al 2021, Trevisiol et al 2021. A classificac ¸ão automática tende a minimizar o esforc ¸o da vetorizac ¸ão manual e encurtar o prazo para obtenc ¸ão dos resultados.…”