Refine
Has Fulltext
- yes (31)
Is part of the Bibliography
- yes (31)
Year of publication
Document Type
- Journal article (30)
- Doctoral Thesis (1)
Language
- English (31) (remove)
Keywords
- Sentinel-2 (5)
- TerraSAR-X (5)
- Google Earth Engine (4)
- PolSAR (4)
- winter wheat (4)
- InSAR (3)
- Radarsat-2 (3)
- SAR (3)
- Sentinel-1 (3)
- arctic (3)
- tundra (3)
- Arctic (2)
- Landsat (2)
- MODIS (2)
- NDVI (2)
- agriculture (2)
- change vector analysis (2)
- coastal erosion (2)
- coherence (2)
- deep learning (2)
- dual polarimetry (2)
- fusion (2)
- geomorphology (2)
- meadow (2)
- paleogeography (2)
- pasture (2)
- permafrost (2)
- radar (2)
- random forest (2)
- remote sensing (2)
- sustainable agriculture (2)
- synthetic aperture RADAR (2)
- time series (2)
- ALOS (1)
- ALOS-2 (1)
- Angola (1)
- Atacama (1)
- Banks Islands (1)
- Blue Spot Analysis (1)
- Canada (1)
- Chile (1)
- Digital Elevation Model (1)
- ENVISAT ASAR WSM (1)
- ERT (1)
- Earth observation (1)
- Formmessung (1)
- Ghana (1)
- Google Earth (1)
- Greenland (1)
- Herodotus (1)
- Iran (1)
- Isheru (1)
- Klassifikation (1)
- LST (1)
- Land Cover Classification (1)
- Landsat 8 (1)
- Landsat archive (1)
- Landsat time series (1)
- MOD13Q1 (1)
- Mackenzie-River-Delta (1)
- Namibia (1)
- Nile Delta (1)
- Nile Delta (Egypt) (1)
- Nile delta (1)
- Nile flow (1)
- Oshana (1)
- PlanetScope (1)
- Polarimetric Synthetic Aperture Radar (PolSAR) (1)
- RADARSAT Constellation Mission (1)
- RADARSAT-2 (1)
- Radarfernerkundung (1)
- Random Forests (1)
- RapidEye (1)
- Relief <Geografie> (1)
- SAR imagery (1)
- STARFM (1)
- Sebennitic (1)
- Sentine-1 (1)
- Sentinel-1 (S-1) synthetic aperture radar (SAR) (1)
- Shannon entropy (1)
- Synthetic Aperture Radar (1)
- Synthetic Aperture Radar (SAR) (1)
- TanDEM-X (1)
- Tell Basta (1)
- Topografie (1)
- WaSiM-ETH (1)
- West Africa (1)
- ancient Egypt (1)
- arctic greening (1)
- beech (1)
- central asia (1)
- change detection (1)
- circum-Arctic (1)
- classification (1)
- climate parameters (1)
- coastline dynamics (1)
- cocoa mapping (1)
- crop growth models (1)
- crop mapping (1)
- crop modeling (1)
- crop models (1)
- cutting (1)
- cutting events (1)
- data fusion (1)
- decision making (1)
- decision-making (1)
- decomposition (1)
- difference water index (1)
- drilling (1)
- drought (1)
- drought stress indicators (1)
- dynamics (1)
- earth observation (1)
- flood (1)
- flood detection (1)
- forest (1)
- forest ecology (1)
- forest hydrology (1)
- galamsey (1)
- geoarchaeology (1)
- geoarcheology (1)
- geographically weighted regression (1)
- geography (1)
- grassland (1)
- gray level co-occurrence matrix (1)
- grazing (1)
- harvests (1)
- hotspot analysis (1)
- image artifacts (1)
- land cover (1)
- landsat (1)
- machine learning (1)
- management (1)
- mangrove ecosystems (1)
- mekong delta (1)
- mining (1)
- mountain pines (1)
- oil seed rape (1)
- oil-seed rape (1)
- optical (1)
- paleoclimate (1)
- paleoenvironment (1)
- pan (1)
- polarimetric decomposition (1)
- polarimetry (1)
- precision agriculture (1)
- quad polarimetry (1)
- resolution (1)
- sacred lakes (1)
- satellite (1)
- sentinel-2 (1)
- shorelines (1)
- snow cover depletion (1)
- spatial error assessment (1)
- storage volume (1)
- sub-pixel coastline extraction (1)
- synthetic aperture radar (1)
- thermal remote sensing (1)
- time-series features (1)
- urban (1)
- water (1)
- water retention (1)
Institute
EU-Project number / Contract (GA) number
- 20-3044-2-11 (1)
The fast and accurate yield estimates with the increasing availability and variety of global satellite products and the rapid development of new algorithms remain a goal for precision agriculture and food security. However, the consistency and reliability of suitable methodologies that provide accurate crop yield outcomes still need to be explored. The study investigates the coupling of crop modeling and machine learning (ML) to improve the yield prediction of winter wheat (WW) and oil seed rape (OSR) and provides examples for the Free State of Bavaria (70,550 km2), Germany, in 2019. The main objectives are to find whether a coupling approach [Light Use Efficiency (LUE) + Random Forest (RF)] would result in better and more accurate yield predictions compared to results provided with other models not using the LUE. Four different RF models [RF1 (input: Normalized Difference Vegetation Index (NDVI)), RF2 (input: climate variables), RF3 (input: NDVI + climate variables), RF4 (input: LUE generated biomass + climate variables)], and one semi-empiric LUE model were designed with different input requirements to find the best predictors of crop monitoring. The results indicate that the individual use of the NDVI (in RF1) and the climate variables (in RF2) could not be the most accurate, reliable, and precise solution for crop monitoring; however, their combined use (in RF3) resulted in higher accuracies. Notably, the study suggested the coupling of the LUE model variables to the RF4 model can reduce the relative root mean square error (RRMSE) from −8% (WW) and −1.6% (OSR) and increase the R
2 by 14.3% (for both WW and OSR), compared to results just relying on LUE. Moreover, the research compares models yield outputs by inputting three different spatial inputs: Sentinel-2(S)-MOD13Q1 (10 m), Landsat (L)-MOD13Q1 (30 m), and MOD13Q1 (MODIS) (250 m). The S-MOD13Q1 data has relatively improved the performance of models with higher mean R
2 [0.80 (WW), 0.69 (OSR)], and lower RRMSE (%) (9.18, 10.21) compared to L-MOD13Q1 (30 m) and MOD13Q1 (250 m). Satellite-based crop biomass, solar radiation, and temperature are found to be the most influential variables in the yield prediction of both crops.