Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method
Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. In this work, we propose a framework to evaluate the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/2/222 |
| _version_ | 1797410160228958208 |
|---|---|
| author | Marcos Ruiz-Aĺvarez Francisco Gomariz-Castillo Francisco Alonso-Sarría |
| author_facet | Marcos Ruiz-Aĺvarez Francisco Gomariz-Castillo Francisco Alonso-Sarría |
| author_sort | Marcos Ruiz-Aĺvarez |
| collection | DOAJ |
| description | Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. In this work, we propose a framework to evaluate the predictive capacity of 11 multi-model ensemble methods (MMEs), including random forest (RF), to estimate reference evapotranspiration (ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula>) using 10 AR5 models for the scenarios RCP4.5 and RCP8.5. The study was carried out in the Segura Hydrographic Demarcation (SE of Spain), a typical Mediterranean semiarid area. ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula> was estimated in the historical scenario (1970–2000) using a spatially calibrated Hargreaves model. MMEs obtained better results than any individual model for reproducing daily ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula>. In validation, RF resulted more accurate than other MMEs (Kling–Gupta efficiency (KGE) <inline-formula><math display="inline"><semantics><mrow><mi>M</mi><mo>=</mo><mn>0.903</mn></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mi>S</mi><mi>D</mi><mo>=</mo><mn>0.034</mn></mrow></semantics></math></inline-formula> for KGE and <inline-formula><math display="inline"><semantics><mrow><mi>M</mi><mo>=</mo><mn>3.17</mn></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mi>S</mi><mi>D</mi><mo>=</mo><mn>2.97</mn></mrow></semantics></math></inline-formula> for absolute percent bias). A statistically significant positive trend was observed along the 21st century for RCP8.5, but this trend stabilizes in the middle of the century for RCP4.5. The observed spatial pattern shows a larger ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula> increase in headwaters and a smaller increase in the coast. |
| first_indexed | 2024-03-09T04:24:55Z |
| format | Article |
| id | doaj.art-7abe62eda5044a7baf64d2e2e7157dd4 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T04:24:55Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-7abe62eda5044a7baf64d2e2e7157dd42023-12-03T13:41:38ZengMDPI AGWater2073-44412021-01-0113222210.3390/w13020222Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble MethodMarcos Ruiz-Aĺvarez0Francisco Gomariz-Castillo1Francisco Alonso-Sarría2University Institute for Water and Environment, University of Murcia, 30100 Murcia, SpainUniversity Institute for Water and Environment, University of Murcia, 30100 Murcia, SpainUniversity Institute for Water and Environment, University of Murcia, 30100 Murcia, SpainLarge ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. In this work, we propose a framework to evaluate the predictive capacity of 11 multi-model ensemble methods (MMEs), including random forest (RF), to estimate reference evapotranspiration (ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula>) using 10 AR5 models for the scenarios RCP4.5 and RCP8.5. The study was carried out in the Segura Hydrographic Demarcation (SE of Spain), a typical Mediterranean semiarid area. ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula> was estimated in the historical scenario (1970–2000) using a spatially calibrated Hargreaves model. MMEs obtained better results than any individual model for reproducing daily ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula>. In validation, RF resulted more accurate than other MMEs (Kling–Gupta efficiency (KGE) <inline-formula><math display="inline"><semantics><mrow><mi>M</mi><mo>=</mo><mn>0.903</mn></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mi>S</mi><mi>D</mi><mo>=</mo><mn>0.034</mn></mrow></semantics></math></inline-formula> for KGE and <inline-formula><math display="inline"><semantics><mrow><mi>M</mi><mo>=</mo><mn>3.17</mn></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mi>S</mi><mi>D</mi><mo>=</mo><mn>2.97</mn></mrow></semantics></math></inline-formula> for absolute percent bias). A statistically significant positive trend was observed along the 21st century for RCP8.5, but this trend stabilizes in the middle of the century for RCP4.5. The observed spatial pattern shows a larger ET<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mn>0</mn></msub></semantics></math></inline-formula> increase in headwaters and a smaller increase in the coast.https://www.mdpi.com/2073-4441/13/2/222random forest regressionreference evapotranspirationmulti-model ensemblesClimate Changefifth assessment reportrandom forest regression kriging |
| spellingShingle | Marcos Ruiz-Aĺvarez Francisco Gomariz-Castillo Francisco Alonso-Sarría Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method Water random forest regression reference evapotranspiration multi-model ensembles Climate Change fifth assessment report random forest regression kriging |
| title | Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method |
| title_full | Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method |
| title_fullStr | Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method |
| title_full_unstemmed | Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method |
| title_short | Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method |
| title_sort | evapotranspiration response to climate change in semi arid areas using random forest as multi model ensemble method |
| topic | random forest regression reference evapotranspiration multi-model ensembles Climate Change fifth assessment report random forest regression kriging |
| url | https://www.mdpi.com/2073-4441/13/2/222 |
| work_keys_str_mv | AT marcosruizalvarez evapotranspirationresponsetoclimatechangeinsemiaridareasusingrandomforestasmultimodelensemblemethod AT franciscogomarizcastillo evapotranspirationresponsetoclimatechangeinsemiaridareasusingrandomforestasmultimodelensemblemethod AT franciscoalonsosarria evapotranspirationresponsetoclimatechangeinsemiaridareasusingrandomforestasmultimodelensemblemethod |