Mapping Seasonal Spatiotemporal Dynamics of Alpine Grassland Forage Phosphorus Using Sentinel-2 MSI and a DRL-GP-Based Symbolic Regression Algorithm

Created by W.Langdon from gp-bibliography.bib Revision:1.8576

@Article{shi:2024:RS,

• author = "Jiancong Shi and Aiwu Zhang and Juan Wang and Xinwang Gao and Shaoxing Hu and Shatuo Chai",
• title = "Mapping Seasonal Spatiotemporal Dynamics of Alpine Grassland Forage Phosphorus Using Sentinel-2 {MSI} and a {DRL-GP-Based} Symbolic Regression Algorithm",
• journal = "Remote Sensing",
• year = "2024",
• volume = "16",
• number = "21",
• pages = "Article No. 4086",
• keywords = "genetic algorithms, genetic programming",
• ISSN = "2072-4292",
• URL = "https://www.mdpi.com/2072-4292/16/21/4086",
• DOI = "doi:10.3390/rs16214086",
• abstract = "An accurate estimation of seasonal spatiotemporal dynamics of forage phosphorus (P) content in alpine grassland is crucial for effective grassland and livestock management. In this study, we integrated Sentinel-2 multispectral imagery (MSI) with computational hyperspectral features (CHSFs) and developed a novel symbolic regression algorithm based on deep reinforcement learning and genetic programming (DRL-GP) to estimate forage P content in alpine grasslands. Using 243 field observations collected during the regreening, grass-bearing, and yellowing periods in 2023 from the Shaliu River Basin, we generated 10 CHSF images (CHSFIs) with varying spectral dispersions (1-10 nm). Our results demonstrated the following: (1) The DRL-GP-based symbolic regression model identified the optimal CHSF and spectral dispersion for each growing season, significantly enhancing estimation accuracy. (2) Forage P content estimations using the combined CHSF and DRL-GP-based symbolic regression algorithm significantly outperformed traditional methods. Compared to original spectral features, the R2 improved by 99.5percent, 57.4percent, and 86.2percent during the regreening, grass-bearing, and yellowing periods, with corresponding MSE reductions of 84.8percent, 41.5percent, and 75.8percent and MAE decreases of 70.7percent, 57.5percent, and 50.4percent. Across these growing seasons, the R2 increased by 322.2percent, 68.2percent, and 639.8percent compared to MLR, 128.9percent, 97.4percent, and 469.2percent compared to RF, and 485.1percent, 65.3percent, and 231.3percent compared to DNN. The MSE decreased by 31percent, 82.9percent, and 52.4percent compared to MLR, 39.9percent, 42.4percent, and 31.4percent compared to RF, and 84.5percent, 73.4percent, and 81.9percent compared to DNN. The MAE decreased by 32.6percent, 67percent, and 44.2percent compared to MLR, 42.6percent, 47.6percent, and 37.9percent compared to RF, and 60.2percent, 50percent, and 56.3percent compared to DNN. (3) Proximity to the water system notably influenced forage P variation, with the highest increases observed within 1-2 km of water sources. These findings provide critical insights for optimising grassland management and improving livestock productivity.",
• notes = "also known as \cite{rs16214086}",

}

Genetic Programming entries for Jiancong Shi Aiwu Zhang Juan Wang Xinwang Gao Shaoxing Hu Shatuo Chai

Citations