An Evolutionary Assisted Machine Learning Model
Back To Blogs List
An evolutionary-assisted machine learning model for global solar radiation prediction in Minas Gerais region, southeastern Brazil
Solar radiation prediction is necessary for designing photovoltaic systems, assessment of regional climate and crop growth modeling. However, this estimate depends on expensive devices, namely pyranometer and pyranometer. Considering the difficulty of acquiring these devices, predicting such values through mathematical and computational models is a convenient approach where costs can be reduced. In particular, machine learning methods have been successfully and widely applied for this task. However, the choice of the correct machine learning model, its parameters sets, and the variables used influence obtained results. This work presents a methodology that optimizes the aforementioned points to efficiently predict solar radiation in the state of Minas Gerais, Brazil. Currently, no work presents a computational model for the entire state. For this, data from 51 cities in Minas Gerais are used, obtained by the automatic weather stations of the National Institute of Meteorology. Two machine learning models, Artificial Neural Network and Multivariate Adaptive Regression Spline, were optimized through a Simple Genetic Algorithm, and the results compared to those available in the literature. The best results were found at the Guanhães station, with R2
of 0.867 and RMSE of 1.68 MJ m−2
day−1
, and at the Muriaé station, with R2
of 0.864 and RMSE of 1.64 MJ m−2
day−1
https://sites.google.com/sanin28.com/flix-i-guardiani-galassia/home
https://sites.google.com/foxtailproject.com/flix01-guardiani-galassia/home
https://sites.google.com/zaksos.com/filmflixguardiani3/home-page
https://sites.google.com/gracemill.co.uk/flix01-i-guardiani-3/home
https://sites.google.com/najat.my.id/altadefinizioneflixguardiani/home
https://sites.google.com/sanin28.com/voirlesgardiensgalaxiev3/home
https://sites.google.com/foxtailproject.com/voirflix-gardiens-3/home
https://sites.google.com/zaksos.com/filmvoirlesgardiensgalaxie3/home-page
https://sites.google.com/gracemill.co.uk/voir-gardiens-galaxie3/home
https://sites.google.com/najat.my.id/flixvoirfilmlesgardiens3/home
https://sites.google.com/sanin28.com/xemvbinhdingnh3/home
https://sites.google.com/zaksos.com/phim-v-binh-di-ngn-h-3/home
https://sites.google.com/sanin28.com/volume-3-hd-kr/home
https://sites.google.com/zaksos.com/vol31080p/home
https://sites.google.com/gracemill.co.uk/guardian32023-hd/home
https://sites.google.com/boncu.online/3guardiansgalaxy-4k/home
https://sites.google.com/gracemill.co.uk/volume32023jphd/home
https://sites.google.com/sanin28.com/gaurdianvol3/home
https://sites.google.com/gracemill.co.uk/2023-jp-hd1080p/home
https://sites.google.com/sanin28.com/mariobrosjp/home
https://sites.google.com/sanin28.com/izlegalaksinin3/home
https://sites.google.com/najat.my.id/galaksinin-koruyucular-3/ana-sayfa
https://sites.google.com/foxtailproject.com/assistir-guardies-da-galxia-vo/home
https://sites.google.com/foxtailproject.com/filmeguardiesdagalxiavol32023f/home
https://open.firstory.me/user/clhowpsrq06qj01uz334cdgsr
https://backlinktool.io/p/jBtkuyb0QLXk23jEmEqg.html
https://argueanything.com/thread/an-evolutionary-assisted-machine-learning-model-for-global-solar/
https://www.onfeetnation.com/photo/albums/fdga4
https://ibusinessday.com/assumption-of-parallelism-in-geological-modelling/
https://caribbeanfever.com/photo/albums/fdga4
http://snaplant.com/question/assumption-of-parallelism-in-geological-modelling/
https://paste.intergen.online/view/194451d2
https://www.kikyus.net/t16083-topic#17457
https://muertadota2.hashnode.dev/we-acknowledge-that-the-modelling-assumption
http://allabouturanch.com/photo/albums/fdga4
https://pastehere.xyz/xzPl5boDn/
https://healingxchange.ning.com/photo/albums/fdga4
https://fnote.net/notes/cq22vG
https://yamcode.com/dsf34-8936
https://ctxt.io/2/AACQe-MVFA
https://justpaste.me/yYTB1
https://pastelink.net/x6pw7ngk
https://homment.com/DjXg4bGrav6FWL6CEnjg
https://rentry.co/3hp9x
https://justpaste.it/9tzwb
https://paste.toolforge.org/view/0bc97571
https://paste.drhack.net/?1e4728458af09102#9AzWxm9kxpAhZUjkUqRJeoaEAwzUEEoFCJbqMvMaKsoA
https://paste.imirhil.fr/?e33aa80286d81d1e#fdK+vVupY+iN0SQzC8meNLAhsFhPXOD/TnsJhBorR9I=
https://controlc.com/e0ed089f
https://etextpad.com/fvxc42kjvq
https://privatebin.net/?6c323fbcf01ee7a7#BH9vGUQApMnEA8isVrfAbhmFjhrTiE3X3Es6f1SbW8MF
https://bitbin.it/Zs0rqbLw/
https://snippet.host/ydwuon
https://pro.pasteshr.in/yxwy1cfwhj
https://www.bankier.pl/forum/temat_the-criteria-to-detect-angular-unconformity,60532011.html
http://pastebin.falz.net/2501209
https://learn.acloud.guru/profile/godsmantownen-ll-l-1
https://godsmantownen.gumroad.com/
https://www.bitsdujour.com/profiles/HqRD9p
http://phillipsservices.net/UserProfile/tabid/43/userId/221652/Default.aspx
http://foxsheets.statfoxsports.com/UserProfile/tabid/57/userId/131991/Default.aspx
https://muckrack.com/godsman-townen/bio
https://www.signalmacc.org/group/holiday-market/discussion/26b50671-2c30-435f-bfb9-1b06ff258ff2
. The models had their metrics compared to each other through the methodology of performance profiles, where the Multivariate Adaptive Regression Spline model proved to be more efficient. The results demonstrate that computational models perform better than the empirical models currently used.
Flood hazard mapping using M5 tree algorithms and logistic regression: a case study in East Black Sea Region
Flood is a type of disaster that occurs as a result of the overflow of the stream outside its bed. Similarly to many parts of the globe, particularly the Eastern Black Sea Region of Turkey is frequently exposed to major floods. The heavy rainfall and topographic structure of the region and the proximity of settlements to stream beds are the primary causes of flooding. The present study pertains to the utilization of the Logistic Regression (LR), M5P Rule Tree (M5PRT) and M5P Regression Tree (M5PRGT) models for the assessment of the flood hazard areas in and around the Of district, located on the Black Sea coast of Trabzon province. According to flood inventory, 16 flood events occurred in 5 different locations in the study area. These areas were converted into point data, and comprising a total of 1600 points, 800 flooded and 800 non-flooded, were determined by random sampling. Accordingly, flood hazard maps were created with 8 flood parameters and 3 different methods. Accuracies of these models were evaluated through AUC (Receiver Operating Characteristics Curve), ACC (Accuracy), R (Recall), P (Precision) and F (F-Score). Analyses showed that the Tree-Based Algorithms are more successful than the LR method in detecting the flood hazards. In addition, the altitude and precipitation were found out to be the most influential parameters in all 3 methods on the occurrence of flooding events in the region. The confluence points of the streams, the coastal plain where the stream disembogues to the sea and the valley floors in and around the Of district were designated as the areas with high risk of flooding.
Geological model automatic reconstruction based on conditioning Wasserstein generative adversarial network with gradient penalty
Due to the structure complexity and heterogeneity of the geological models, it is difficult for traditional methods to characterize the corresponding anisotropic and structural features. Therefore, one of the generative models called Generative Adversarial Network (GAN) are introduced to the geological modeling fields, which describes the complex structural features effectively according to fitting the high-order statistical characteristics. However, the traditional GAN might cause gradient explosion or vanishment, insufficient model diversity, resulting the network cannot capture the spatial pattern and characteristics of geological models so that the reconstruction always has a bad performance. For this issue, this paper introduced the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), which can better measure the distribution discrepancy between the generative data and real data and provide a meaningful gradient for the training process. In addition, the gradient penalty term can make the objective function conform with Lipschitz constraints, which ensures the training process more stable and the correlation between the generative and real samples. Meanwhile, the conditioning loss function can make the reconstruction conform with the conditioning constraints. The 2D and 3D categorical facies model were introduced to perform experimental verification. The results show that the CWGAN-GP ensure the conditioning constraints and the reconstruction diversity simultaneously. In addition, for the network finished training, through inputting different kinds of conditioning data, a variety of stochastic simulation results can be generated, thereby realizing rapid and automatic geological model reconstruction.
Comments