The ARYA crop yield forecasting algorithm: Application to the main wheat exporting countries

被引:14
作者
Franch, B. [1 ,2 ]
Vermote, E. [3 ]
Skakun, S. [2 ,3 ]
Santamaria-Artigas, A. [2 ,3 ]
Kalecinski, N. [2 ,3 ]
Roger, J-C [2 ,3 ]
Becker-Reshef, I [2 ]
Barker, B. [2 ]
Justice, C. [2 ]
Sobrino, J. A. [1 ]
机构
[1] Univ Valencia, Global Change Unit, Image Proc Lab, Valencia 46980, Spain
[2] Univ Maryland, Dept Geog Sci, College Pk, MD 20742 USA
[3] NASA, Goddard Space Flight Ctr, Code 619,8800 Greenbelt Rd, Greenbelt, MD 20771 USA
关键词
Agriculture; Wheat; Yield forecast; MODIS; DVI; LST; GROWING DEGREE-DAYS; BIDIRECTIONAL REFLECTANCE; WINTER-WHEAT; UNITED-STATES; MODIS; SURFACE; MODEL; TEMPERATURE; REANALYSIS; RETRIEVAL;
D O I
10.1016/j.jag.2021.102552
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Wheat is the most important commodity traded in the international food market. Thus, accurate and timely information on wheat production can help mitigate food price fluctuations. Within the existing operational regional and global scale agricultural monitoring systems that provide information on global crop yield and area forecasts, there are still fundamental gaps: #1. Lack of quantitative Earth Observation (EO) derived crop in-formation, #2. Lack of global but detailed (national or subnational level) and timely crop production forecasts and #3. Lack of information on forecast uncertainties. In this study we present the Agriculture Remotely-sensed Yield Algorithm (ARYA) an EO-based method, advancing the state of EO-data application and usage (addressing gap #1) to forecast wheat yield. The algorithm is based on the evolution of the Difference Vegetation Index (DVI) using MODIS data at 1 km resolution and the Growing Degree Days (GDD) from reanalysis data. Additionally, we explore how Land Surface Temperature (LST) can be included into the model and whether this parameter adds any value to the model performance when combined with the optical information. ARYA is implemented at the national and subnational level to forecast winter wheat yield in the main wheat exporting countries of US, Russia, Ukraine, France, Germany, Australia and Argentina from 2001 to 2019 (covering over 70% of wheat exports globally) in a timely manner by providing daily forecasts (addressing gap #2). The results show that ARYA provides yield estimations with RMSE's within 0.3 +/- 0.1 t/ha at national level and 0.6 +/- 0,1 t/ha at subnational level after Day Of the Year (DOY) 140 (mid May) in the Northern Hemisphere and DOY 280 (beginning of October) in the Southern Hemisphere. This means that ARYA can provide crop yield estimates of wheat yield with 5-15% error at national and 7-20% error at subnational level starting from 2 to 2.5 months prior to harvest.
引用
收藏
页数:20
相关论文
共 55 条
[1]   Permutation importance: a corrected feature importance measure [J].
Altmann, Andre ;
Tolosi, Laura ;
Sander, Oliver ;
Lengauer, Thomas .
BIOINFORMATICS, 2010, 26 (10) :1340-1347
[2]   The Evaporative Stress Index as an indicator of agricultural drought in Brazil: An assessment based on crop yield impacts [J].
Anderson, Martha C. ;
Zolin, Cornelio A. ;
Sentelhas, Paulo C. ;
Hain, Christopher R. ;
Semmens, Kathryn ;
Yilmaz, M. Tugrul ;
Gao, Feng ;
Otkin, Jason A. ;
Tetrault, Robert .
REMOTE SENSING OF ENVIRONMENT, 2016, 174 :82-99
[3]   Evaluation of Drought Indices Based on Thermal Remote Sensing of Evapotranspiration over the Continental United States [J].
Anderson, Martha C. ;
Hain, Christopher ;
Wardlow, Brian ;
Pimstein, Agustin ;
Mecikalski, John R. ;
Kustas, William P. .
JOURNAL OF CLIMATE, 2011, 24 (08) :2025-2044
[4]  
Anderson S., 2014, Journal of Agricultural Education, V55, P132, DOI [10.5032/jae.2014.03132, DOI 10.5032/JAE.2014.03132]
[5]   POTENTIALS AND LIMITS OF VEGETATION INDEXES FOR LAI AND APAR ASSESSMENT [J].
BARET, F ;
GUYOT, G .
REMOTE SENSING OF ENVIRONMENT, 1991, 35 (2-3) :161-173
[6]  
Baruth Bettina., 2008, Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci, V37, P935
[7]  
Becker-Reshef I, 2018, INT GEOSCI REMOTE SE, P8155, DOI 10.1109/IGARSS.2018.8517575
[8]   A generalized regression-based model for forecasting winter wheat yields in Kansas and Ukraine using MODIS data [J].
Becker-Reshef, I. ;
Vermote, E. ;
Lindeman, M. ;
Justice, C. .
REMOTE SENSING OF ENVIRONMENT, 2010, 114 (06) :1312-1323
[9]   The GEOGLAM crop monitor for AMIS: Assessing crop conditions in the context of global markets [J].
Becker-Reshef, Inbal ;
Barker, Brian ;
Humber, Michael ;
Puricelli, Estefania ;
Sanchez, Antonio ;
Sahajpal, Ritvik ;
McGaughey, Katie ;
Justice, Christopher ;
Baruth, Bettina ;
Wu, Bingfang ;
Prakash, Adam ;
Abdolreza, Abbassian ;
Jarvis, Ian .
GLOBAL FOOD SECURITY-AGRICULTURE POLICY ECONOMICS AND ENVIRONMENT, 2019, 23 :173-181
[10]   Causes and implications of the unforeseen 2016 extreme yield loss in the breadbasket of France [J].
Ben-Ari, Tamara ;
Boe, Julien ;
Ciais, Philippe ;
Lecerf, Remi ;
Van der Velde, Marijn ;
Makowski, David .
NATURE COMMUNICATIONS, 2018, 9