Prediction models establishment and comparison for guiding force of high-temperature superconducting maglev based on deep learning algorithms

By the merits of self-stability and low energy consumption, high temperature superconducting (HTS) maglev has the potential to become a novel type of transportation mode. As a key index to guarantee the lateral self-stability of HTS maglev, guiding force has strong non-linearity and is determined by multitudinous factors, and these complexities impede its further researches. Compared to traditional finite element and polynomial fitting method, the prosperity of deep learning algorithms could provide another guiding force prediction approach, but the verification of this approach is still blank. Therefore, this paper establishes 5 different neural network models (RBF, DNN, CNN, RNN, LSTM) to predict HTS maglev guiding force, and compares their prediction efficiency based on 3720 pieces of collected data. Meanwhile, two adaptively iterative algorithms for parameters matrix and learning rate adjustment are proposed, which could effectively reduce computing time and unnecessary iterations. And according to the results, it is revealed that, the DNN model shows the best fitting goodness, while the LSTM model displays the smoothest fitting curve on guiding force prediction. Based on this discovery, the effects of learning rate and iterations on prediction accuracy of the constructed DNN model are studied. And the learning rate and iterations at the highest guiding force prediction accuracy are 0.00025 and 90000, respectively. Moreover, the K-fold cross validation method is also applied to this DNN model, whose result manifests the generalization and robustness of this DNN model. The imperative of K-fold cross validation method to ensure universality of guiding force prediction model is likewise assessed. This paper firstly combines HTS maglev guiding force prediction with deep learning algorithms considering different field cooling height, real-time magnetic flux density, liquid nitrogen temperature and motion direction of bulk. Additionally, this paper gives a convenient and efficient method for HTS guiding force prediction and parameter optimization.

A global evaluation of IMERG precipitation occurrence using SMAP detected soil moisture change

A globally consistent ground validation method for remotely sensed precipitation products is crucial for building confidence in these products. This study develops a new methodology to validate the IMERG precipitation products through the use of SMAP soil moisture changes as a proxy for precipitation occurrence. Using a standard 2x2 contingency table method, preliminary results provide confidence in SMAP’s ability to be utilized as a validation tool for IMERG as results are comparable to previous validation studies. However, the method allows for an overestimate of false alarm frequency due to light precipitation events that can evaporate before the subsequent SMAP overpass and changes in overpass-to-overpass SMAP soil moisture that are within the range of SMAP uncertainty. To counter these issues, a 3x3 contingency table is used to reduce noise and extract more signal from the detection method. Through the use of this novel approach, the validation method produces a global mean POD of 0.64 and global mean FAR of 0.40, the first global-scale ground validation skill scores for the IMERG products. Advancing the method to validate precipitation quantity and the development of a real-time validation for the IMERG Early product are the crucial next developments.

Development of an experiment-split method for benchmarking the generalization of a PTM site predictor: Lysine methylome as an example

Many computational classifiers have been developed to predict different types of post-translational modification sites. Their performances are measured using cross-validation or independent test, in which experimental data from different sources are mixed and randomly split into training and test sets. However, the self-reported performances of most classifiers based on this measure are generally higher than their performances in the application of new experimental data. It suggests that the cross-validation method overestimates the generalization ability of a classifier. Here, we proposed a generalization estimate method, dubbed experiment-split test, where the experimental sources for the training set are different from those for the test set that simulate the data derived from a new experiment. We took the prediction of lysine methylome (Kme) as an example and developed a deep learning-based Kme site predictor (called DeepKme) with outstanding performance. We assessed the experiment-split test by comparing it with the cross-validation method. We found that the performance measured using the experiment-split test is lower than that measured in terms of cross-validation. As the test data of the experiment-split method were derived from an independent experimental source, this method could reflect the generalization of the predictor. Therefore, we believe that the experiment-split method can be applied to benchmark the practical performance of a given PTM model. DeepKme is free accessible via https://github.com/guoyangzou/DeepKme.

MILKSHAKE: novel validation method for antibodies to post-translationally modified targets by surrogate Western blot

Antibody (Ab) validation is the procedure in which an Ab is thoroughly assayed for sensitivity and specificity in a given application. Validation of Abs against post-translationally modified (PTM) targets is particularly challenging because it requires specifically prepared antigen. Here we describe a novel validation method using surrogate proteins in a Western blot. The surrogate protein, which we termed ‘MILKSHAKE,’ is a modified maltose binding protein enzymatically conjugated to a peptide from the chosen target that is either modified or nonmodified at the residue of interest. The certainty of the residue’s modification status can be used to confirm Ab specificity. This method also allows for Ab validation even in the absence or limited availability of treated cell lysates.