GeoUNet: A novel AI model for high-resolution mapping of ecological footprint

Ye, Ruilin; Huang, Zhou; Li, Linna; Shan, Xv

doi:10.1016/j.jag.2022.102803

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of deep learning, convolutional neural networks (CNN) are steadily displacing conventional techniques and are increasingly used for feature extraction in high‐resolution remote sensing (Ball et al., 2017; Yuan et al., 2020; Ye et al, 2022). ResNet is a novel CNN‐based model that utilizes residual blocks to increase the depth of traditional CNN and avoid the degradation problem of deep networks (He et al., 2016).…”

Section: Methods and Datamentioning

confidence: 99%

High‐resolution quantification of building stock using multi‐source remote sensing imagery and deep learning

Bao

Huang

Wang

et al. 2023

J of Industrial Ecology

Self Cite

View full text Add to dashboard Cite

In recent decades, urbanization has led to an increase in building material stock. The high‐resolution quantification of building stock is essential to understand the spatial concentration of materials, urban mining potential, and sustainable urban development. Current approaches rely excessively on statistics or survey data, both of which are unavailable for most cities, particularly in underdeveloped areas. This study proposes an end‐to‐end deep‐learning model based on multi‐source remote sensing data, enabling the reliable estimation of building stock. Ground‐detail features extracted from optical remote sensing (ORS) and spatiotemporal features extracted from nighttime light (NTL) data are fused and incorporated into the model to improve accuracy. We also compare the performance of our feature‐fusion model with that of an ORS‐only regression model and traditional NTL regression for Beijing. The proposed model yields the best building‐stock estimation, with a Spearman's rank correlation coefficient of 0.69, weighted root mean square error of 0.58, and total error in the test set below 14%. Using gradient‐weighted class activation mapping, we further investigate the relationship between ORS features and building‐stock estimation. Our model exhibits reliable predictive capability and illustrates the tremendous value of the physical environment for estimating building stock. This research illustrates the significant potential of ORS and deep learning for stock estimation. Large‐scale, long‐term building‐stock investigations could also benefit from the end‐to‐end predictability and the data availability of the model.

show abstract

Section: Methods and Datamentioning

confidence: 99%

High‐resolution quantification of building stock using multi‐source remote sensing imagery and deep learning

Bao

Huang

Wang

et al. 2023

J of Industrial Ecology

Self Cite

View full text Add to dashboard Cite

show abstract

Monthly electricity consumption data at 1 km × 1 km grid for 280 cities in China from 2012 to 2019

Yan,

Huang,

Ren

et al. 2024

Sci Data

View full text Add to dashboard Cite

High spatio-temporal resolution estimates of electricity consumption are essential for formulating effective energy transition strategies. However, the data availability is limited by complex spatio-temporal heterogeneity and insufficient multi-source feature fusion. To address these issues, this study introduces an innovative downscaling method that combines multi-source data with machine learning and spatial interpolation techniques. The method’s accuracy showed significant improvements, with determination coefficients ( R 2 ) increasing by 30.1% and 33.4% over the baseline model in two evaluation datasets. With this advanced model, we estimated monthly electricity consumption across 1 km x 1 km grid for 280 Chinese cities from 2012 to 2019. Our dataset is highly consistent with officially released electricity consumption of different industries (Pearson correlation coefficients within 0.83 - 0.91). Moreover, our data can reflect the electricity consumption patterns of different urban land uses compared to other datasets. This study bridges a significant gap in fine-grained electricity consumption data, providing a robust foundation for the development of sustainable energy policies.

show abstract

GeoUNet: A novel AI model for high-resolution mapping of ecological footprint

Cited by 2 publications

References 41 publications

High‐resolution quantification of building stock using multi‐source remote sensing imagery and deep learning

High‐resolution quantification of building stock using multi‐source remote sensing imagery and deep learning

Monthly electricity consumption data at 1 km × 1 km grid for 280 cities in China from 2012 to 2019

Contact Info

Product

Resources

About