Rice yield forecasting models using satellite imagery in Egypt

Abstract Density-free and variable-density empirical yield prediction equations were constructed from stand level data collected from 28 plots established in all of the European latch plantations known to have been successfully established on abandoned farmlands in central Maine prior to 1983. Results can be used directly to predict future plantation yields or incorporated in yield forecasting models. North. J. Appl. For. 13(1):37-40.

Download Full-text

Rice Yield Forecasting in West Bengal Using Hybrid Model

10.1007/978-981-16-4486-3_24 ◽

2021 ◽

pp. 222-231

Author(s):

Aishika Banik ◽

G. Raju ◽

Samiksha Shukla

Keyword(s):

Hybrid Model ◽

West Bengal ◽

Rice Yield ◽

Yield Forecasting

Download Full-text

PENGEMBANGAN PENGGUNAAN PENGINDERAAN JAUH UNTUK ESTIMASI PRODUKSI PADI (STUDI KASUS KABUPATEN BEKASI)

Jurnal Ilmu Tanah dan Lingkungan ◽

10.29244/jitl.19.1.6-12 ◽

2019 ◽

Vol 19 (1) ◽

pp. 6-12

Author(s):

Eka Rudiana ◽

Ernan Rustiadi ◽

Muhammad Firdaus ◽

Dede Dirgahayu

Keyword(s):

Satellite Imagery ◽

Vegetation Index ◽

Rice Yield ◽

Equation Model ◽

Rice Production ◽

Landsat 8 ◽

Landsat 8 Oli ◽

Enhanced Vegetation Index ◽

The One ◽

The Relationship

The utilization of remote sensing imagery such Landsat-8 (OLI) to estimate harvested area and yield using Enhanced Vegetation Index (EVI) parameter is a new approach to estimate regional rice production. Based on the analysis of the satellite imagery acquisition during May-August 2015, the estimation of rice harvested area in Bekasi District during July-October 2015 is 15.86 thousand ha or 7.74 thousand ha (32.79%) lower than BPS figures in the same period. Based on the relationship between yield (from the crop cutting survei, BPS) and EVI maximum, the equation model for rice yield estimation is: Yield (qu ha-1) = 36.818 + 44.965 EVImax. R2 value is 0.809. Based on the model, the estimation of rice yield in Bekasi District during July-October 2015 is 47.40 qu ha-1. Compared to the data published by BPS, the result is 12.66 qu ha-1 lower than the yield figure in subround I 2015, 6.77 qu ha-1 lower than the one in subround II 2015, 10.15 qu ha-1 lower than the one subround III 2015, and 6.62 qu ha-1 lower than the one in January-December 2015. Meanwhile, based on satellite imagery analysis, the estimation of rice production in the period of July-October 2015 is 75.16 thousand tons of GKG or 55.35 thousand tons of GKG (42.41%) lower than BPS figures during the same period. Keywords: Enhanced Vegetation Index, Landsat-8 (OLI), rice production estimation

Download Full-text

Spatiotemporal Optimization for Short-Term Solar Forecasting Based on Satellite Imagery

Energies ◽

10.3390/en14082216 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2216

Author(s):

Myeongchan Oh ◽

Chang Ki Kim ◽

Boyoung Kim ◽

Changyeol Yun ◽

Yong-Heack Kang ◽

...

Keyword(s):

Satellite Imagery ◽

Spatial Data ◽

Motion Vector ◽

Satellite Image ◽

Skill Score ◽

Solar Forecasting ◽

Short Term ◽

Forecast Horizon ◽

Forecasting Models ◽

Optimized Model

Solar forecasting is essential for optimizing the integration of solar photovoltaic energy into a power grid. This study presents solar forecasting models based on satellite imagery. The cloud motion vector (CMV) model is the most popular satellite-image-based solar forecasting model. However, it assumes constant cloud states, and its accuracy is, thus, influenced by changes in local weather characteristics. To overcome this limitation, satellite images are used to provide spatial data for a new spatiotemporal optimized model for solar forecasting. Four satellite-image-based solar forecasting models (a persistence model, CMV, and two proposed models that use clear-sky index change) are evaluated. The error distributions of the models and their spatial characteristics over the test area are analyzed. All models exhibited different performances according to the forecast horizon and location. Spatiotemporal optimization of the best model is then conducted using best-model maps, and our results show that the skill score of the optimized model is 21% better than the previous CMV model. It is, thus, considered to be appropriate for use in short-term forecasting over large areas. The results of this study are expected to promote the use of spatial data in solar forecasting models, which could improve their accuracy and provide various insights for the planning and operation of photovoltaic plants.

Download Full-text