Advancement of a diagnostic prediction model for spatiotemporal calibration of earth observation data: a case study on projecting forest net primary production in the mid-latitude region

Park, E., Jo, H.-W., Biging, G.S., Chun, J.A., Jeon, S.W., Son, Y., Kraxner, F., & Lee, W.-K. (2024). Advancement of a diagnostic prediction model for spatiotemporal calibration of earth observation data: a case study on projecting forest net primary production in the mid-latitude region. GIScience & Remote Sensing 61 (1) e2401247. 10.1080/15481603.2024.2401247.

Preview

Text Advancement of a diagnostic prediction model for spatiotemporal calibration of earth observation data a case study on projecting forest net primary p.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. Download (26MB) | Preview

Abstract

Developing a precise and interpretable spatiotemporal model is need for establishing evidence-based adaptation strategies on climate change-driven disasters. This study introduced a diagnostic prediction concept as a generalized modeling framework for enhancing modeling precision and interpretability and demonstrate a case study of estimating forest net primary production (NPP) in a mid-latitude region (MLR) by developing a diagnostic NPP diagnostic prediction model (DNPM). The diagnostic prediction concept starts with modeling meteorology and static environmental data, referred as a prognostic prediction part. Then, its outcome is refined with spatiotemporal residual calibration in the diagnostic prediction part, of which result undergo spatial, temporal, and spatiotemporally explicit validation methods. For the case of DNPM, a prognostic NPP prediction model (PNPM) was set, using a multilinear regression on SPEI 3, temperature, and static environmental features extracted from topography and soil by a random forest. Subsequently, during the diagnostic process of DNPM, we calibrated the primary outcome based on the temporal pattern captured at the time-series residual of PNPM. The results highlighted the superiority of the DNPM over the PNPM. Spatiotemporal validation showed that the DNPM achieved higher accuracy, with Pearson correlation coefficients ((Formula presented.)) ranging from 0.975 to 0.992 and root mean squared error (RMSE) between 38.99 and 70.23 gC/m2/year across all climate zones. Similarly, temporal validation indicated that DNPM outperformed the PNPM, with (Formula presented.) values of 0.233 to 0.494 and RMSE of 46.01 to 70.75 gC/m2/year, compared to the PNPM’s (Formula presented.) values of 0.192 to 0.406 and RMSE of 55.23 to 89.31 gC/m2/year. This study showed enhanced diagnostic prediction concept can be applied to diverse environmental modeling approaches, offering valuable insights for climate adaptation and forest policy formulation. By accurately predicting various environmental targets, including drought and forest NPP, this approach aids in making informed policy decisions across different scales.

Actions (login required)

View Item