| 1. |
- Hu, Yifan, et al.
(författare)
-
Reconstructing long-term global satellite-based soil moisture data using deep learning method
- 2023
-
Ingår i: Frontiers in Earth Science. - : Frontiers Media SA. - 2296-6463. ; 11
-
Tidskriftsartikel (refereegranskat)abstract
- Soil moisture is an essential component for the planetary balance between land surface water and energy. Obtaining long-term global soil moisture data is important for understanding the water cycle changes in the warming climate. To date several satellite soil moisture products are being developed with varying retrieval algorithms, however with considerable missing values. To resolve the data gaps, here we have constructed two global satellite soil moisture products, i.e., the CCI (Climate Change Initiative soil moisture, 1989–2021; CCIori hereafter) and the CM (Correlation Merging soil moisture, 2006–2019; CMori hereafter) products separately using a Convolutional Neural Network (CNN) with autoencoding approach, which considers soil moisture variability in both time and space. The reconstructed datasets, namely CCIrec and CMrec, are cross-evaluated with artificial missing values, and further againt in-situ observations from 12 networks including 485 stations globally, with multiple error metrics of correlation coefficients (R), bias, root mean square errors (RMSE) and unbiased root mean square error (ubRMSE) respectively. The cross-validation results show that the reconstructed missing values have high R (0.987 and 0.974, respectively) and low RMSE (0.015 and 0.032 m3/m3, respectively) with the original ones. The in-situ validation shows that the global mean R between CCIrec (CCIori) and in-situ observations is 0.590 (0.581), RMSE is 0.093 (0.093) m3/m3, ubRMSE is 0.059 (0.058) m3/m3, bias is 0.032 (0.037) m3/m3 respectively; CMrec (CMori) shows quite similar results. The added value of this study is to provide long-term gap-free satellite soil moisture products globally, which helps studies in the fields of hydrology, meteorology, ecology and climate sciences.
|
|
| 2. |
- Wang, Yifan, et al.
(författare)
-
Time delay recursive neural network-based direct adaptive control for a piezo-actuated stage
- 2023
-
Ingår i: Science China Technological Sciences. - 1869-1900 .- 1674-7321. ; 66:5, s. 1397-1407
-
Tidskriftsartikel (refereegranskat)abstract
- Piezo-actuated stage is a core component in micro-nano manufacturing field. However, the inherent nonlinearity, such as rate-dependent hysteresis, in the piezo-actuated stage severely impacts its tracking accuracy. This study proposes a direct adaptive control (DAC) method to realize high precision tracking. The proposed controller is designed by a time delay recursive neural network. Compared with those existing DAC methods designed under the general Lipschitz condition, the proposed control method can be easily generalized to the actual systems, which have hysteresis behavior. Then, a hopfield neural network (HNN) estimator is proposed to adjust the parameters of the proposed controller online. Meanwhile, a modular model consisting of linear submodel, hysteresis submodel, and lumped uncertainties is established based on the HNN estimator to describe the piezo-actuated stage in this study. Thus, the performance of the HNN estimator can be exhibited visually through the modeling results. The proposed control method eradicates the adverse effects on the control performance arising from the inaccuracy in establishing the offline model and improves the capability to suppress the influence of hysteresis on the tracking accuracy of piezo-actuated stage in comparison with the conventional DAC methods. The stability of the control system is studied. Finally, a series of comparison experiments with a dual neural networks-based data driven adaptive controller are carried out to demonstrate the superiority of the proposed controller.
|
|
| 3. |
- Zhou, Yifan, et al.
(författare)
-
Insights into health promoting effects and myochemical profiles of pine mushroom Tricholoma matsutake
- 2023
-
Ingår i: Critical reviews in food science and nutrition. - : Taylor & Francis. - 1040-8398 .- 1549-7852. ; 63:22, s. 5698-5723
-
Forskningsöversikt (refereegranskat)abstract
- Tricholoma matsutake (TM) is a valuable edible mushroom that has attracted increasing attention due to its potential medicinal values and functional uses. However, the chemical composition and molecular mechanisms behinds TM are not specifically summarized yet. Hence, this review aims to systematically analyze the research progress on the characterization of chemical compositions and the reported health effects of TM in the last 20 years. The myochemical profiles of TM consist of proteins with amino acids, fatty acids, nucleic acids with their derivatives, polysaccharides, minerals, volatile components, phenolic compounds, and steroids. The bioactive substances in TM exert their health effects mainly by regulating body immunity and restoring the balance of the redox system. NF-kappa B signaling pathway and its downstream cytokines such as TNF-alpha and IL-6 are the key molecular mechanisms. In addition, MAPK, PI3K-Akt, and JAK-STAT are also involved. NF-kappa B, MAPK, and PI3K-Akt are also highly related to cancer regulation and thus TM has great anticancer potential. Considering that most studies have only investigated the dosage and inhibition rate of TM on cancer cell lines, more extensive studies need to focus on the specific molecular mechanisms behind these anticancer effects in the future.
|
|
