View in EDS HTML Full Text PDF Full Text

Multi-Source Meteorological–Topographic Modeling of Monthly Power Generation for Mountain Photovoltaic Stations Using Gradient-Boosted Trees.

Saved in:
Bibliographic Details
Title: Multi-Source Meteorological–Topographic Modeling of Monthly Power Generation for Mountain Photovoltaic Stations Using Gradient-Boosted Trees.
Authors: Sun, Pengjie1 (AUTHOR), Wang, Ming1 (AUTHOR) wangming@lasg.iap.ac.cn, Meng, Dan1 (AUTHOR), Xu, Yang1 (AUTHOR), Cheng, Chi1 (AUTHOR), Ju, Wei1 (AUTHOR)
Source: Energies (19961073). Jun2026, Vol. 19 Issue 12, p2936. 22p.
Subject Terms: *Solar power plants, *Prediction models, *Global radiation, *Meteorological databases, *Landforms, *Ensemble learning
Geographic Terms: China, Hubei Sheng (China)
Abstract: Mountain photovoltaic (PV) stations are increasingly deployed in complex terrain, where generation is jointly controlled by solar-resource variability, near-surface meteorology, and local topography. However, the quantitative contribution of topographic factors to regional-scale PV generation remains insufficiently evaluated, and many prediction studies rely on single-station or short-term records. In this study, monthly measured generation from 118 standardized village-level mountain PV stations in Badong County, western Hubei Province, China (2019–2021), was integrated with Solargis Global Horizontal Irradiance (GHI)-related solar-resource data, high-resolution gridded meteorological data, a 25 m digital elevation model, seasonal-cycle variables, and historical-generation features. After seasonally grouped median-absolute-deviation (MAD) outlier screening, GIS-based spatial matching, terrain extraction, and viewshed-derived shading analysis, regression models and climatology baselines were compared under both chronological validation and station-exclusion spatial cross-validation. Under the strict chronological validation, CatBoost achieved the best temporal performance among the tested models (R2 = 0.3119, MAE = 2719.7 kWh, RMSE = 3245.6 kWh), slightly outperforming the monthly climatology baseline. In the station-exclusion spatial cross-validation, XGBoost achieved the highest mean R2 (0.8659), indicating good spatial transferability to unseen stations. Correlation and partial-correlation analyses showed that the temperature-related variable group and monthly radiation were the dominant meteorological controls, whereas elevation, slope, and terrain shading showed weak direct correlations with monthly generation for already-sited stations. Annual 90% prediction intervals were further estimated using residual bootstrapping, with an empirical coverage of 94.9%. The proposed framework provides a practical basis for monthly generation forecasting and operational assessment of already-built distributed PV stations in mountainous regions, while its application to greenfield site selection requires additional site engineering and near-field obstruction information. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194909385
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multi-Source Meteorological–Topographic Modeling of Monthly Power Generation for Mountain Photovoltaic Stations Using Gradient-Boosted Trees.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sun%2C+Pengjie%22">Sun, Pengjie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Ming%22">Wang, Ming</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wangming@lasg.iap.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Meng%2C+Dan%22">Meng, Dan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Yang%22">Xu, Yang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cheng%2C+Chi%22">Cheng, Chi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ju%2C+Wei%22">Ju, Wei</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Jun2026, Vol. 19 Issue 12, p2936. 22p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Solar+power+plants%22">Solar power plants</searchLink><br />*<searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br />*<searchLink fieldCode="DE" term="%22Global+radiation%22">Global radiation</searchLink><br />*<searchLink fieldCode="DE" term="%22Meteorological+databases%22">Meteorological databases</searchLink><br />*<searchLink fieldCode="DE" term="%22Landforms%22">Landforms</searchLink><br />*<searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22China%22">China</searchLink><br /><searchLink fieldCode="DE" term="%22Hubei+Sheng+%28China%29%22">Hubei Sheng (China)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Mountain photovoltaic (PV) stations are increasingly deployed in complex terrain, where generation is jointly controlled by solar-resource variability, near-surface meteorology, and local topography. However, the quantitative contribution of topographic factors to regional-scale PV generation remains insufficiently evaluated, and many prediction studies rely on single-station or short-term records. In this study, monthly measured generation from 118 standardized village-level mountain PV stations in Badong County, western Hubei Province, China (2019–2021), was integrated with Solargis Global Horizontal Irradiance (GHI)-related solar-resource data, high-resolution gridded meteorological data, a 25 m digital elevation model, seasonal-cycle variables, and historical-generation features. After seasonally grouped median-absolute-deviation (MAD) outlier screening, GIS-based spatial matching, terrain extraction, and viewshed-derived shading analysis, regression models and climatology baselines were compared under both chronological validation and station-exclusion spatial cross-validation. Under the strict chronological validation, CatBoost achieved the best temporal performance among the tested models (R2 = 0.3119, MAE = 2719.7 kWh, RMSE = 3245.6 kWh), slightly outperforming the monthly climatology baseline. In the station-exclusion spatial cross-validation, XGBoost achieved the highest mean R2 (0.8659), indicating good spatial transferability to unseen stations. Correlation and partial-correlation analyses showed that the temperature-related variable group and monthly radiation were the dominant meteorological controls, whereas elevation, slope, and terrain shading showed weak direct correlations with monthly generation for already-sited stations. Annual 90% prediction intervals were further estimated using residual bootstrapping, with an empirical coverage of 94.9%. The proposed framework provides a practical basis for monthly generation forecasting and operational assessment of already-built distributed PV stations in mountainous regions, while its application to greenfield site selection requires additional site engineering and near-field obstruction information. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194909385
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19122936
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 22
        StartPage: 2936
    Subjects:
      – SubjectFull: Solar power plants
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Global radiation
        Type: general
      – SubjectFull: Meteorological databases
        Type: general
      – SubjectFull: Landforms
        Type: general
      – SubjectFull: Ensemble learning
        Type: general
      – SubjectFull: China
        Type: general
      – SubjectFull: Hubei Sheng (China)
        Type: general
    Titles:
      – TitleFull: Multi-Source Meteorological–Topographic Modeling of Monthly Power Generation for Mountain Photovoltaic Stations Using Gradient-Boosted Trees.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sun, Pengjie
      – PersonEntity:
          Name:
            NameFull: Wang, Ming
      – PersonEntity:
          Name:
            NameFull: Meng, Dan
      – PersonEntity:
          Name:
            NameFull: Xu, Yang
      – PersonEntity:
          Name:
            NameFull: Cheng, Chi
      – PersonEntity:
          Name:
            NameFull: Ju, Wei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1