Incident Solar Radiation Prediction Revisited

New synthetic data informed the ML model to improve the prediction results by half. In the previous test the mean distance between prediction and real measure was ~23.70. Now the distance was reduced to ~8.25.

One of the main advantages of synthetic data is that can be moulded to the problem. For the revisited excercise the feautures ZU, YX, widht and length were replaced for Area1, Area2, Area3, Area4, Area5. These new features represents the facade areas of the building. In addition to these new features, ang1, ang2, ang3, ang4 and ang5 were also added, and represents the angle between the nomal on the facade surfaces and the project North.

A very useful matrix to understand the shape of data is the correlation matrix. It is useful to understand the relationship between 2 variables in the dataset. Typically, to quantify the relationship the Pearson correlation coefficient is used:

  • -1 indicates a perfectly negative linear correlation between two variables
  • 0 indicates no linear correlation between two variables
  • 1 indicates a perfectly positive linear correlation between two variables

Therefore, the further away the correlation coefficient is from 0, the stronger relationship between the 2 variables is.


Correlation matrix comparison between the previous dataset on the left and the new dataset on the right.

Correlation Matrix Comparison

The correlation matrix on the left is from the previous test. The prediction of the total target is mainly based on 3 features: YX, ZU and volume. The features angle, length and width have a limited influence in the ML model. The other 3 layers do not participate in the prediction, that is why the white mask on top of these cells.

The correlation matrix on the right incorporate the new features discribed previously. For this excercise the prediction of the total is based on 6 features: Area1, Area2, Area3, Area4, Area5 and volume. The other 6 features, related with the angles of the building have an small impact in the prediction. It worth to mention the angle in the revisted exercise hast a correlation coefient of 0.056 in contrast to the previous test: 0.043. It gets more importance to predict the feature total.

The new synthetic data generated added new useful features to predict the total solar radiation. In addition, the new data optimized the distribution of the features weights.



The images above shows the results between prediction and solar radiation measures from the software. The X axis indicates the different independent tests. from A to K in the left and from A to M in the right. The Y axis indicates the total sun radiation. The diamonds represents the real measures and the blue circles the predictions.

The tests inside the circles, represents very close measure and prediction results. Its easy to see how accurate was the second test (blue circles) incomparison to the 1st test, in green. The mean distance between measure and prediction in the first graphic is 23.7047, while in the revisted version: 8.2596. This implies an accurate prediction in comparison to the previous test.

An interesting point is the ML model did not changed at all. Yet, the data to train the model it's different.


Add a comment


Written on Fri, 31 Mar 2023 02:46:51 by

Замечательно, очень забавное мнение of males in the uk and 16% of women.|Six years ago, I exited the porn business after the studio i labored for succumbed to a decline in dvd sales.

Written on Thu, 30 Mar 2023 09:36:02 by

Какой прелестный топик the sandwich automated trading technique detects when traders place bids on a particular cryptocurrency.

Written on Wed, 22 Mar 2023 19:46:40 by

Великолепная фраза сайт genesis market - market.

Written on Wed, 22 Mar 2023 09:58:26 by

Однозначно, отличное сообщение

Written on Tue, 21 Mar 2023 20:56:40 by

Вы абсолютно правы. В этом что-то есть и мысль хорошая, согласен с Вами. maybe you’ll attempt your luck on the ships 1win online casino.

Written on Sun, 19 Mar 2023 00:39:44 by

Я думаю, что Вы не правы. Я уверен. Могу это доказать. Пишите мне в PM, пообщаемся. --- Москва не сразу строилась. 21 блэкджек как играть, играть блэкджек с друзьями и блэкджек играть онлайн на раздевание

Written on Sat, 18 Mar 2023 16:27:39 by

Вы ошибаетесь. Пишите мне в PM, пообщаемся. --- Это забавное мнение grammar writing courses, writing articles courses а также writing courses for children

Written on Fri, 17 Mar 2023 15:34:42 by

officers who're the central factors for the coordination of federal, State and college funds. Therefore, there is no such thing as a

Written on Fri, 17 Mar 2023 04:05:07 by

Written on Mon, 13 Mar 2023 02:41:08 by

Я думаю, что Вы ошибаетесь. Давайте обсудим. Пишите мне в PM. goes to area truly essential throughout a cooler bag

Written on Tue, 07 Mar 2023 20:10:05 by

Эта мысль придется как раз кстати --- Поздравляю, вас посетила просто великолепная мысль verle кофе купить, lavazza купить кофе а также кофе музетти купить

Written on Tue, 07 Mar 2023 16:02:28 by

Вы попали в самую точку. Мне нравится эта мысль, я полностью с Вами согласен.

Written on Sun, 05 Mar 2023 09:25:50 by

Hello. And Bye. https://webtest345687534xvhfd3333.xer

Written on Tue, 14 Feb 2023 01:58:33 by

Hello. And Bye. https://webtest345687534xvhfd3333.xer

Written on Thu, 02 Feb 2023 19:09:16 by

Я думаю, что это хорошая идея.

Written on Tue, 10 Jan 2023 19:15:55 by

Доставка из Европы в Россию. Как выбрать транспортную компанию или Как выбрать офисный диван бу?