Soft Periodic Convolutional Recurrent Network for Spatiotemporal Climate Forecast

Many machine-learning applications and methods are emerging to solve problems associated with spatiotemporal climate forecasting; however, a prediction algorithm that considers only short-range sequential information may not be adequate to deal with periodic patterns such as seasonality. In this paper, we adopt a Periodic Convolutional Recurrent Network (Periodic-CRN) model to employ the periodicity component in our proposals of the periodic representation dictionary (PRD). Phase shifts and non-stationarity of periodicity are the key components in the model to support. Specifically, we propose a Soft Periodic-CRN (SP-CRN) with three proposals of utilizing periodicity components: nearby-time (PRD-1), periodic-depth (PRD-2), and periodic-depth differencing (PRD-3) representation to improve climate forecasting accuracy. We experimented on geopotential height at 300 hPa (ZH300) and sea surface temperature (SST) datasets of ERA-Interim. The results showed the superiority of PRD-1 plus or minus one month of a prior cycle to capture the phase shift. In addition, PRD-3 considered only the depth of one differencing periodic cycle (i.e., the previous year) can significantly improve the prediction accuracy of ZH300 and SST. The mixed method of PRD-1, and PRD-3 (SP-CRN-1+3) showed a competitive or slight improvement over their base models. By adding the metadata component to indicate the month with one-hot encoding to SP-CRN-1+3, the prediction result was a drastic improvement. The results showed that the proposed method could learn four years of periodicity from the data, which may relate to the El Niño–Southern Oscillation (ENSO) cycle.

Enhancing Monthly Lake Levels Forecasting Using Heuristic Regression Techniques with Periodicity Data Component: Application of Lake Michigan

This paper investigates the accuracy of three different techniques with periodicity component for estimation of monthly lake levels. The compared methods are Least Square Support Vector Regression (LSSVR) Multivariate Adaptive Regression Splines (MARS) and M5 Model Tree (M5-Tree). Data from Lake Michigan, located in the USA, is used in the analysis. In the first stage of the study, three different techniques were applied to forecast monthly lake-levels variations up to 8- mount ahead of time intervals. In the second stage, the influence of the periodicity component was applied (month number of the year, e.g., 1, 2, 3, …12) as an external sub-set in modeling monthly lake levels. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) were utilized are used for evaluating the accuracy of models. In both stages, the comparison results indicate that the MARS model generally performs superior to the LSSVR, and M5-Tree models. Furthermore, it has been discovered that including periodicity as an input to the models improves their accuracy in projecting monthly lake levels.

Measurement of the Straightness of a Leadscrew-Driven Precision Stage

This paper describes a multi-probe method for measuring the straightness error of a leadscrew-driven stage. Two displacement probes are employed to scan a flat artifact mounted on the stage. The surface profile error of the flat artifact is separated from the straightness error of the stage in a differential output of the probes. The straightness error can thus be obtained accurately from an integration operation of the differential output without the influence of the surface profile error. An improved technique of data processing is adopted for measurement of straightness error components with periodicity shorter than the probe spacing. The influence of the angular error of the stage is compensated for by using the result measured by an autocollimator. Experiments of straightness measurement of a leadscrew-driven stage with a lead of 1 mm were carried out by using two flat artifacts with different degrees of precision. The successful detection of the short-periodicity component of the straightness error with a periodicity equal to the lead indicated the feasibility of the multi-probe method.