Fast magnitude determination using a single seismological station record implementing machine learning techniques

In this work a Support Vector Machine Regression（SVMR） algorithm is used to calculate local magnitude（MI） using only five seconds of signal after the P wave onset of one three component seismic station. This algorithm was trained with 863 records of historical earthquakes, where the input regression parameters were an exponential function of the waveform envelope estimated by least squares and the maximum value of the observed waveform for each component in a single station. Ten-fold cross validation was applied for a normalized polynomial kernel obtaining the mean absolute error for different exponents and complexity parameters. The local magnitude（MI） could be estimated with 0.19 units of mean absolute error. The proposed algorithm is easy to implement in hardware and may be used directly after the field seismological sensor to generate fast decisions at seismological control centers, increasing the possibility of having an effective reaction.

Quantifying Multi-hazards and Impacts Over Different Growth Periods of Maize:A Study Based on Index Construction

Owing to the complexity and variability of global climate,the study of extreme events to ensure food security is particularly critical.The standardized precipitation requirement index(SPRI)and chilling injury index(I_(Ci))were introduced using data from agrometeorological stations on the Songliao Plain between 1981 and 2020 to identify the spatial and temporal variability of drought,waterlogging,and low-temperature cold damage during various maize growth periods.Compound drought and low-temperature cold damage events(CDLEs)and compound waterlogging and low-temperature cold damage events(CWLEs)were then identified.To measure the intensity of compound events,the compound drought and low-temperature cold damage magnitude index(CDLMI),and compound waterlogging and low-temperature cold damage magnitude index(CWLMI)were constructed by fitting marginal distributions.Finally,the effects of extreme events of various intensities on maize output were examined.The findings demonstrate that:(1)There were significant differences in the temporal trends of the SPRI and ICiduring different maize growth periods.Drought predominated in the middle growth period(MP),waterlogging predominated in the early growth period(EP)and late growth period(LP),and both drought and waterlogging tended to increase in intensity and frequency.The frequency of low-temperature cold damage showed a decreasing trend in all periods.(2)The CDLMI and CWLMI can effectively determine the intensity of CDLEs and CWLEs in the study area;these CDLEs and CWLEs had higher intensity and frequency in the late growth period.(3)Compared to single events,maize relative meteorological yield had a more significant negative correlation with the CDLMI and CWLMI.