Abnormally high water temperature prediction using LSTM deep learning model

2021 ◽  
pp. 1-8
Author(s):  
Hey-Min Choi ◽  
Min-Kyu Kim ◽  
Hyun Yang
Keyword(s):  
Deep Learning ◽  
Water Temperature ◽  
Short Term Memory ◽  
High Water ◽  
Percentage Error ◽  
Southern Coast ◽  
High Water Temperature ◽  
Decision Algorithm ◽  
Water Temperature Data ◽  
Vibrio Pathogens

Recently, abnormally high water temperature (AHWT) phenomena are occurring more often due to the global warming and its impact. These phenomena have damaged extensively to the maritime economy around the southern coast of Korea and caused an illness by exacerbating the propagation of Vibrio pathogens. To mitigate damages by AHWT phenomena, it is necessary to respond as quickly as possible or predict them in advance. In this study, therefore, we proposed a deep learning-based methodology to predict the occurrences of AHWT phenomena using the long short-term memory (LSTM) model. First, a LSTM model was trained using the satellite-derived water temperature data over the past ten years. Then, the water temperatures after a few days were estimated using the trained LSTM model. In a performance evaluation, when estimating water temperatures after one-day, the model achieved results of 1.865 and 0.412 in terms of mean absolute percentage error (MAPE) and root mean square error (RMSE), respectively. Second, we developed a decision algorithm based on the Markov state transition in order to predict the AHWT occurrence probability. As a result, we obtained 0.88 of F1 score for predicting AHWT phenomena after 1 day in case of the southern coast of Korea.

PP15 Predicting variations of calls to an ambulance service in the UK caused by circulating infections using-deep learning methods

2019 ◽  
Vol 36 (10) ◽  
pp. e7.2-e7
Author(s):  
Thilo Reich ◽  
Marcin Budka
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Prehospital Care ◽  
Machine Learning Algorithms ◽  
Ambulance Service ◽  
Percentage Error ◽  
Learning Methods ◽  
Average Percentage ◽  
Average Percentage Error ◽  
The Uk

BackgroundDigital patient records in the ambulance service have opened up new opportunities for prehospital care. Previously it was demonstrated that prehospital pyrexia numbers are linked to an increase in overall calls to the ambulance service. This study aims to predict the future number of calls using deep-learning methods.MethodsTemperature readings for 280,447 patients were generously provided by the South Western Ambulance Service Trust. The data covered the time between 05/01/2016 and 30/04/2017 with overall 44,472 patients being pyretic. A rolling window of 10 days was applied to daily sums for both pyretic and apyretic patients. These windows were used as input features to train machine-learning algorithms predicting the number of calls 10 days ahead. Algorithms tested include Linear Regression (LR), basic Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures. A genetic approach was used to optimise the architecture, in which parameters were randomly modified and over several generations the best performing algorithm will be selected to be further manipulated. To assess performance the Mean Average Percentage Error (MAPE) was used.ResultsThe initial analysis showed that the total patient number and pyretic patient numbers are correlated. The best performing algorithms with varying numbers of hidden units had the following MAPE in comparison to simple LR: LR=19.4%, LSTM (104 units) = 6.1%, RNN (79 units)=6.01%, GRU (80 units)=5.97%.ConclusionsThese preliminary results suggest that deep-learning methods allow to predict the variations in total number of calls caused by circulating infections. Further investigations will aim to confirm these findings. Once fully verified these algorithms could play a major role in operational planning of any ambulance service by predicting increases in demand.

scholarly journals The Monthly Variation Process of Water Temperature in Jiaozhou Bay

2019 ◽  
Vol 136 ◽  
pp. 06015
Author(s):  
Dongfang Yang ◽  
Haoyuan Ren ◽  
Dong Yang ◽  
Longlei Zhang ◽  
Haixia Li
Keyword(s):  
Water Temperature ◽  
Jiaozhou Bay ◽  
High Water ◽  
Water Bodies ◽  
Interval Length ◽  
Monthly Variation ◽  
High Water Temperature ◽  
Water Field ◽  
Variation Process ◽  
Peak Value

According to the investigation materials in the water field of Jiaozhou Bay from May to October 1980, this paper studies the water temperature of Jiaozhou Bay and the monthly variation. The results show that in each monthfrom May to October, the water temperature varies from 10.80 to 26.53 °C in the waters of Jiaozhou Bay, and the interval length of water temperature is 15.73 °C. This paper determines the changing curve of the high or low value of the water temperature ateach month and establishes the corresponding simulation equation.The high water temperature reaches a maximum of 26.53 °C in August, and the low water temperature reaches a maximum of 24.69 °C in August. In the water bodies of Jiaozhou Bay, the high or low water temperature both reaches its highest value in August. In June, the increasing rate of peak value in water temperature is the fastest, and the increasing rate of low value in water temperature is relatively fast. In October, the decreasing rate of the peak water temperature is relatively fast, and decreasing rateof the lowest value in water temperature is the fastest. From May to August, the high (low) water temperature is on the rise in Jiaozhou Bay. The high water temperature appears in the western waters of the top of bay and the western waters inside of bay mouth. The low water temperature appears in the eastern and southern waters outside of bay mouth. In September and October, the high (low) water temperature in the Jiaozhou Bay water bodies is decreasing. The high water temperature appears in the eastern and southern waters outside of bay mouth, and the low water temperature appears in the western waters of the bayhead.

scholarly journals The breeding ecology of the pipefish Nerophis lumbriciformis and its relation to latitude and water temperature

2001 ◽  
Vol 81 (6) ◽  
pp. 1031-1033 ◽  
Author(s):  
N. Monteiro ◽  
V.C. Almada ◽  
A.M. Santos ◽  
M.N. Vieira
Keyword(s):  
Water Temperature ◽  
Breeding Season ◽  
Marked Reduction ◽  
High Water ◽  
Inhibitory Effect ◽  
Breeding Ecology ◽  
High Water Temperature ◽  
Temporal Differences ◽  
Breeding Activity ◽  
Different Temperatures

The breeding season of Nerophis lumbriciformis (Pisces: Syngnathidae), has not yet been determined for the southernmost part of its range. A total of 863 individuals was examined between March 1997 and November 1999. In Portugal, the breeding season of this species occurs throughout the year, with a marked reduction during summer and autumn, whilst in Britain it occurs from May to September. Despite these temporal differences, the water temperature at which breeding takes place is similar in the two areas (13–16°C). Together with preliminary laboratory observations with animals kept at different temperatures, these data support the hypothesis that the decrease in breeding activity during summer and autumn in Portugal is due to an inhibitory effect of high water temperature.

Sign in / Sign up

Export Citation Format

Share Document