Agricultural and Forest Meteorology

• A novel memory-based deep learning framework was proposed for joint estimation of daily GPP, RECO, and NEE. • The proposed model achieved robust daily carbon flux estimations with enhanced reliability. • The linear probes revealed the increased reliability of the proposed model through better correlation in predicting non-target variables, i.e. vegetation transpiration and canopy conductance. •…

• Integrating physiological knowledge with machine learning improves GPP estimation. • Process models convert environmental data to meaningful inputs for neural networks. • With abundant training data, the model achieved higher accuracy than baseline models. • Physiological features prevented overfitting under limited training data conditions. • Our hybrid approach shows potential for adaptation …

• Tree species responded differently to short-term dry spells across growth phases. • Beech trees were more drought-resistant than Norway spruce and Scots pine, maintaining stem growth during early and main growth phases. • Scots pine and Norway spruce showed growth reduction after only three consecutive dry days, whereas beech growth declined only in the late phase after seven dry days. • Soil m…

• Turbulent transport dissimilarities are observed even on ideal underlying surfaces. • The dissimilarities are accompanied by the transitions of coherent structures. • Prevailing coherent structures and its role under each stability regime are depicted. Turbulent transport dissimilarities among momentum, heat, and passive scalars challenge the application of Monin-Obukhov similarity theory in la…