Presentation is loading. Please wait.

Presentation is loading. Please wait.

A Development and Parallelization of an air temperature Spatial Interpolation and Prediction Program Student: Erik LaBerge Advisor: Munihiro Fukuda.

Similar presentations


Presentation on theme: "A Development and Parallelization of an air temperature Spatial Interpolation and Prediction Program Student: Erik LaBerge Advisor: Munihiro Fukuda."— Presentation transcript:

1 A Development and Parallelization of an air temperature Spatial Interpolation and Prediction Program Student: Erik LaBerge Advisor: Munihiro Fukuda

2 Overview of Project Goal: Protect crops from frost damage How: Fans, sprinklers My part: Find out when to use fans/sprinklers – Monitor current temperatures – Predict future temperatures

3 Definition of Work Code Algorithms: – Air Temperature Spatial Interpolation Algorithms Inverse Distance Weighting Polynomial Regression – Air Temperature Prediction Algorithms Polynomial Prediction Artificial Neural Network Verify results with historical and mock-up data Improve accuracy by altering algorithms Compare performance between algorithms

4 Process of Data from Interpolation to Prediction Receive data from sensors – Latitude, longitude, elevation, temperature Interpolate data from known to unknown points and output a grid encompassing all of the sensor points Predict temperature from the interpolated data for an overnight period, to determine the minimum expected temperature

5 Inverse Distance Weighting Input data – From dispersed points Create a grid encompassing all data points Estimate all points in the grid based on the known data

6 Inverse Distance Weighting Cont. Red: High Temperature Blue: Low Temperature Red: High Temperature Blue: Low Temperature

7 Inverse Distance Weighting Cont. Red: High Temperature Blue: Low Temperature Red: High Temperature Blue: Low Temperature

8 Polynomial Regression Y = (Latitude)*x_1 + (Longitude)*x_2 + (Elevation)*x_3 Y = (Latitude)*x_1 + (Longitude)*x_2 + (Elevation)*x_3

9 Polynomial Regression Cont. Red: High Temperature Blue: Low Temperature Red: High Temperature Blue: Low Temperature

10 Polynomial Prediction

11 Artificial Neural Network To get prediction: Temperature * weight ->signal -> a() -> signal signal -> b() -> signal signal -> c() -> signal * weight -> signal +_________ signal -> activate() -> prediction |-------- 1 st feed forward --------| |--------------4 th feed forward--------------| |---- 3 rd feed forward -----| |--2 nd feed forward--|

12 Artificial Neural Network Cont. To initialize: Temperature -> Target -> Learn Rate -> test() -> Error -> --------> Learn Rate -> backPropegate() -> returns errors and changes weights based on the derivative of the presignal, error value, and learn rate

13 Artificial Neural Network Cont. 7pm 9pm 11pm 1am 3am 5am8am Actual temperature Predicted temperature 7am

14 Inverse Distance WeightingPolynomial Regression Calculating a 600 by 1100 space from 191 data points 40 seconds7 seconds Calculating a 600 by 1100 space from 1200 data points Temperature Interpolation Performance Since we will use not only (longitude, latitude, altitude) but also wind, etc., we should use inverse distance weighting for temperature interpolation

15 Polynomial PredictionArtificial Neural Network (ANN) Calculating predictions from 191 sensors Initialization: none Single prediction: 0.000188 sec Initialization: 1.253 ~ 1.6 sec Single prediction: 0.204 ~ 0.305 sec Calculating predictions from 1200 sensors 0.000188 sec * 1200 = 0.2256 sec(0.25 sec * 1200) + 1.255 = 301.255 sec Temperature Prediction Performance ANN will be used for the first 4-5 hours and Polynomial Prediction will be used for the rest of the prediction duration. So we need 301.26 + 0.23 = 301.49sec for prediction every 10 minutes.

16 Performance Cont. The total processing time every 10 minutes is: 251.31 + 301.26 + 0.23 = 552.8 sec -> 9.21 min Factors that could make it slower are: – More sensors(900MHz + WiFi combination). Increasing the amount of time interpolating data – Factoring in more variables such as wind, bodies of water, neighboring sensors’ data

17 Conclusion Interpolation and prediction can be done within a reasonable degree of accuracy when combining different methods Lessons learned: – Object orientation – Verify results incrementally – Reuse code


Download ppt "A Development and Parallelization of an air temperature Spatial Interpolation and Prediction Program Student: Erik LaBerge Advisor: Munihiro Fukuda."

Similar presentations


Ads by Google