A high-resolution machine learning and multi-source remote sensing approach for estimating net primary productivity in campus green spaces

Chien-Hao Sung; Candera Wijaya; Aji Kusumaning Asri; Yinq-Rong Chern; Tee-Ann Teo; Wan-Yu Liu; Chia-Ho Lee; Yu-Liang Hsu; Chih-Da Wu

doi:10.1038/s41598-025-28350-6

A high-resolution machine learning and multi-source remote sensing approach for estimating net primary productivity in campus green spaces

Sci Rep. 2025 Dec 24;15(1):44609. doi: 10.1038/s41598-025-28350-6.

Authors

Chien-Hao Sung¹, Candera Wijaya², Aji Kusumaning Asri¹, Yinq-Rong Chern¹, Tee-Ann Teo³, Wan-Yu Liu^{4

5}, Chia-Ho Lee⁶, Yu-Liang Hsu⁷, Chih-Da Wu^{8

9

10

11

12

13}

Affiliations

¹ Department of Geomatics, College of Engineering, National Cheng Kung University, Tainan, 70101, Taiwan.
² Agricultural Engineering Research Center, Taoyuan, 32061, Taiwan.
³ Department of Civil Engineering, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd., East District, Hsinchu City, 300, Taiwan.
⁴ Department of Forestry, National Chung Hsing University, Taichung City, 402, Taiwan.
⁵ Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Taichung City, 402, Taiwan.
⁶ Chiayi City Environmental Protection Bureau, No. 184, Wu Feng North Road, Chiayi City, 60045, Taiwan.
⁷ Department of Architecture, National Cheng Kung University, 1 University Rd., East District, Tainan, 701, Taiwan.
⁸ Department of Geomatics, College of Engineering, National Cheng Kung University, Tainan, 70101, Taiwan. chidawu@mail.ncku.edu.tw.
⁹ Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Taichung City, 402, Taiwan. chidawu@mail.ncku.edu.tw.
¹⁰ Department of Architecture, National Cheng Kung University, 1 University Rd., East District, Tainan, 701, Taiwan. chidawu@mail.ncku.edu.tw.
¹¹ National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, 35053, Taiwan. chidawu@mail.ncku.edu.tw.
¹² Research Center for Precision Environmental Medicine, Kaohsiung Medical University, Kaohsiung, 807, Taiwan. chidawu@mail.ncku.edu.tw.
¹³ Chronic Diseases and Health Promotion Research Center, Chang Gung University of Science and Technology (CGUST), Chiayi, 613, Taiwan. chidawu@mail.ncku.edu.tw.

Abstract

This research proposes an innovative framework that integrates Machine Learning classification, the Carnegie-Ames-Stanford Approach (CASA), unmanned aerial vehicles (UAV), and multi-source data to estimate the net primary productivity (NPP) of campus green spaces. Green space was extracted using Random Forest with an overall accuracy of 94.6% (Kappa = 0.919). The fraction of Photosynthetically Active Radiation (FPAR) was derived from UAV multispectral vegetation indices, while temperature, solar radiation, and the Water Stress Factor (WSF) estimated from Sentinel 2 imagery were integrated into CASA to model NPP. Validation showed that our approach offered higher R² and lower RMSE compared to traditional CASA. Across two seasons, the model achieved R² values of 0.68-0.79, with RMSE of 11.74-17.01 gC·m^-2·month^-1 and RRMSE of 15.63-22.65%. Seasonal dynamics and human activities explained the observed variation in R², RMSE, and RRMSE. Our scalable approach suggests that campus green spaces have the potential to serve as contributors to urban carbon sinks. This method has strong potential to inform sustainable urban planning, carbon offset programs, and nature-based climate solutions.

Keywords: Carnegie-Ames-Stanford Approach (CASA); Net Primary Productivity; Random Forest Classification; Unmanned Aerial Vehicle (UAV) Multispectral Image; Urban Green Space.

Abstract

Grants and funding