Prediction of Cloud Fractional Cover Using Machine Learning
Climate change is stated as one of the largest issues of our time, resulting in many unwanted effects on life on earth. Cloud fractional cover (CFC), the portion of the sky covered by clouds, might affect global warming and different other aspects of human society such as agriculture and solar energ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/5/4/62 |
| _version_ | 1797506566467878912 |
|---|---|
| author | Hanna Svennevik Michael A. Riegler Steven Hicks Trude Storelvmo Hugo L. Hammer |
| author_facet | Hanna Svennevik Michael A. Riegler Steven Hicks Trude Storelvmo Hugo L. Hammer |
| author_sort | Hanna Svennevik |
| collection | DOAJ |
| description | Climate change is stated as one of the largest issues of our time, resulting in many unwanted effects on life on earth. Cloud fractional cover (CFC), the portion of the sky covered by clouds, might affect global warming and different other aspects of human society such as agriculture and solar energy production. It is therefore important to improve the projection of future CFC, which is usually projected using numerical climate methods. In this paper, we explore the potential of using machine learning as part of a statistical downscaling framework to project future CFC. We are not aware of any other research that has explored this. We evaluated the potential of two different methods, a convolutional long short-term memory model (ConvLSTM) and a multiple regression equation, to predict CFC from other environmental variables. The predictions were associated with much uncertainty indicating that there might not be much information in the environmental variables used in the study to predict CFC. Overall the regression equation performed the best, but the ConvLSTM was the better performing model along some coastal and mountain areas. All aspects of the research analyses are explained including data preparation, model development, ML training, performance evaluation and visualization. |
| first_indexed | 2024-03-10T04:34:22Z |
| format | Article |
| id | doaj.art-12523b854e6345f28c2b8d112bdc6729 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-10T04:34:22Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-12523b854e6345f28c2b8d112bdc67292023-11-23T03:51:07ZengMDPI AGBig Data and Cognitive Computing2504-22892021-11-01546210.3390/bdcc5040062Prediction of Cloud Fractional Cover Using Machine LearningHanna Svennevik0Michael A. Riegler1Steven Hicks2Trude Storelvmo3Hugo L. Hammer4Department of Geosciences, University of Oslo, 0316 Oslo, NorwayDepartment of Computer Science, University of Tromsø, 9037 Tromsø, NorwaySimulaMet, 0167 Oslo, NorwayDepartment of Geosciences, University of Oslo, 0316 Oslo, NorwaySimulaMet, 0167 Oslo, NorwayClimate change is stated as one of the largest issues of our time, resulting in many unwanted effects on life on earth. Cloud fractional cover (CFC), the portion of the sky covered by clouds, might affect global warming and different other aspects of human society such as agriculture and solar energy production. It is therefore important to improve the projection of future CFC, which is usually projected using numerical climate methods. In this paper, we explore the potential of using machine learning as part of a statistical downscaling framework to project future CFC. We are not aware of any other research that has explored this. We evaluated the potential of two different methods, a convolutional long short-term memory model (ConvLSTM) and a multiple regression equation, to predict CFC from other environmental variables. The predictions were associated with much uncertainty indicating that there might not be much information in the environmental variables used in the study to predict CFC. Overall the regression equation performed the best, but the ConvLSTM was the better performing model along some coastal and mountain areas. All aspects of the research analyses are explained including data preparation, model development, ML training, performance evaluation and visualization.https://www.mdpi.com/2504-2289/5/4/62climate sciencecloud fractional coverdeep learningmachine learningstatistical downscaling |
| spellingShingle | Hanna Svennevik Michael A. Riegler Steven Hicks Trude Storelvmo Hugo L. Hammer Prediction of Cloud Fractional Cover Using Machine Learning Big Data and Cognitive Computing climate science cloud fractional cover deep learning machine learning statistical downscaling |
| title | Prediction of Cloud Fractional Cover Using Machine Learning |
| title_full | Prediction of Cloud Fractional Cover Using Machine Learning |
| title_fullStr | Prediction of Cloud Fractional Cover Using Machine Learning |
| title_full_unstemmed | Prediction of Cloud Fractional Cover Using Machine Learning |
| title_short | Prediction of Cloud Fractional Cover Using Machine Learning |
| title_sort | prediction of cloud fractional cover using machine learning |
| topic | climate science cloud fractional cover deep learning machine learning statistical downscaling |
| url | https://www.mdpi.com/2504-2289/5/4/62 |
| work_keys_str_mv | AT hannasvennevik predictionofcloudfractionalcoverusingmachinelearning AT michaelariegler predictionofcloudfractionalcoverusingmachinelearning AT stevenhicks predictionofcloudfractionalcoverusingmachinelearning AT trudestorelvmo predictionofcloudfractionalcoverusingmachinelearning AT hugolhammer predictionofcloudfractionalcoverusingmachinelearning |