Understanding and Modeling Climate Impacts on Photosynthetic Dynamics with FLUXNET Data and Neural Networks

Zhu, Nanyan; Liu, Chen; Laine, Andrew F.; Guo, Jia

doi:10.3390/en13061322

Cited by 5 publications

(2 citation statements)

References 23 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach yielded substantial validation accuracy, as indicated by an R-squared value of 0.75. In studies where different models were used to predict the global GPP, researchers found that the LSTM model consistently had the lowest RMSE [23]. Chen [24] used an LSTM model with temperature and precipitation data as input variables to predict future changes in vegetation NDVI.…”

Section: Introductionmentioning

confidence: 99%

Normal Difference Vegetation Index Simulation and Driving Analysis of the Tibetan Plateau Based on Deep Learning Algorithms

Liu,

Du,

et al. 2024

Forests

View full text Add to dashboard Cite

Global climate warming has profoundly affected terrestrial ecosystems. The Tibetan Plateau (TP) is an ecologically vulnerable region that emerged as an ideal place for investigating the mechanisms of vegetation response to climate change. In this study, we constructed an annual synthetic NDVI dataset with 500 m resolution based on MOD13A1 products from 2000 to 2021, which were extracted by the Google Earth Engine (GEE) and processed by the Kalman filter. Furthermore, considering topographic and climatic factors, a thorough analysis was conducted to ascertain the causes and effects of the NDVI’s spatiotemporal variations on the TP. The main findings are: (1) The vegetation coverage on the TP has been growing slowly over the past 22 years at a rate of 0.0134/10a, with a notable heterogeneity due to its topography and climate conditions. (2) During the study period, the TP generally showed a “warming and humidification” trend. The influence of human activities on vegetation growth has exhibited a favorable trajectory, with a notable acceleration observed since 2011. (3) The primary factor influencing NDVI in the southeastern and western regions of the TP was the increasing temperature. Conversely, vegetation in the northeastern and central regions was mostly regulated by precipitation. (4) Combined with the principal component analysis, a PCA-CNN-LSTM (PCL) model demonstrated significant superiority in modeling NDVI sequences on the Tibetan Plateau. Understanding the results of this paper is important for the sustainable development and the formulation of ecological policies on the Tibetan Plateau.

show abstract

Section: Introductionmentioning

confidence: 99%

Normal Difference Vegetation Index Simulation and Driving Analysis of the Tibetan Plateau Based on Deep Learning Algorithms

Liu,

Du,

et al. 2024

Forests

View full text Add to dashboard Cite

show abstract

“…In [6], a Deep Neural Network (DNN) model of the temporal dynamics of plant photosynthesis related to the gross primary product is established for two types of vegetations. Three architectures of DNN models are designed in the study, respectively.…”

Section: Introductionmentioning

confidence: 99%

Net Photosynthesis Prediction by Deep Learning for Commercial Greenhouse Production

Clausen

Jôrgensen

2021

2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES)

View full text Add to dashboard Cite

The amount of net photosynthesis of leaves is a significate factor for the growth of plants. Therefore, monitoring the real-time net photosynthesis plays an essential role in improving the quality of productions in commercial greenhouses. Net photosynthesis mainly depends on three environmental parameters, that are light level, temperature and CO2 concentration. However, it is challenging to calculate accurate net photosynthesis due to the highly nonlinear relation. In this paper, Deep Learning (DL) is utilized to model this relationship in order to predict the net photosynthesis based on the three inputs. Firstly, the architecture of a Deep Neural Network (DNN) model is designed according to the features of this problem, and three activation functions are concerned for the DNN model design. Secondly, a training dataset is established, and two schedules of Learning Rate (LR), fixed LR and exponential decay LR, are elaborated. Then, to select the optimal hyperparameters for the DNN model, experiments of hyperparameters tuning related to activation functions and LR schedules are implemented, respectively. Finally, through a comprehensive evaluation of the training speed and the prediction accuracy, a DNN model that is with ReLU activation function and decay LR is determined. This DNN model can perform a dramatically high prediction accuracy in a fast training convergence speed for solving the proposed net photosynthesis prediction problem.

show abstract

Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction

Zhang,

Alvandipour,

Xia

et al. 2024

J Sci Comput

View full text Add to dashboard Cite

Understanding and Modeling Climate Impacts on Photosynthetic Dynamics with FLUXNET Data and Neural Networks

Cited by 5 publications

References 23 publications

Normal Difference Vegetation Index Simulation and Driving Analysis of the Tibetan Plateau Based on Deep Learning Algorithms

Normal Difference Vegetation Index Simulation and Driving Analysis of the Tibetan Plateau Based on Deep Learning Algorithms

Net Photosynthesis Prediction by Deep Learning for Commercial Greenhouse Production

Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction

Contact Info

Product

Resources

About