Use of interpretive machine learning and a crop model to investigate the impact of environment and management on soybean yield gap
Alireza Nehbandani
A * , Patrick Filippi B , Parisa Alizadeh-Dehkordi C , Amir Dadrasi D and Afshin Soltani A
A
B
C
D
Abstract
Management and environmental conditions are the main factors influencing yield of soybean (Glycine max (L.) Merr.). Despite an increase in average soybean yield in recent years in Iran, a considerable gap remains between actual yield and potential yield.
The objective of this study was to identify critical climate and management factors affecting soybean yield in Iran’s major soybean production area.
A combination of machine learning approaches (using gradient boosted decision trees, XGBoost) and the SSM-iCrop2 simulation model was used. Critical management factors affecting soybean yield were determined through interpretive machine learning using information collected from 268 soybean fields over a 5-year period. Potential yield and water-limited potential yield at six weather stations were estimated for 30 years via the SSM-iCrop2 simulation model. Water limitation was determined by considering the ratio of water-limited yield potential to potential yield, and heat stress status was quantified as the number of days with maximum temperature >36°C during the soybean growing season.
The XGBoost models adequately described the observed changes in soybean yield. Root-mean-square error and Lin’s concordance correlation coefficient values of the calibrated model were 262 kg ha−1 and 0.96, respectively, which indicated that the predictor variables could describe most of the variation in soybean yield for the studied dataset.
We identified 15 climatic and management variables that affect soybean yield. A large part of the studied area is under high water stress and low heat stress.
Optimal planting date and improved irrigation management are the main options for reducing the yield gap in the study area.
Keywords: heat stress, irrigation, planting date, potential yield, Shapley additive explanation values, SSM_iCrop2, water limitation, water-limited yield potential.
References
Agudamu , Yoshihira T, Shiraiwa T (2016) Branch development responses to planting density and yield stability in soybean cultivars. Plant Production Science 19(3), 331-339.
| Crossref | Google Scholar |
Ahmadi SAK, Daneshian J (2014) Effect of sowing date on seed yield of soybean genotypes and determination of threshold of temperature stress in North Khouzestan conditions. Seed and Plant Production Journal 30(2), 135-152.
| Crossref | Google Scholar |
Amiri AM, Dadashi MR, Faraji A (2018) Investigation of affecting factors on soybean (Glycine max L.) pod abnormality in Gorgan. Journal of Crop Ecophysiology 12, 337-354.
| Google Scholar |
Andrade JF, Mourtzinis S, Edreira JIR, et al. (2022) Field validation of a farmer supplied data approach to close soybean yield gaps in the US North Central region. Agricultural Systems 200, 103434.
| Crossref | Google Scholar |
Ball RA, Purcell LC, Vories ED (2000) Optimizing soybean plant population for a short-season production system in the southern USA. Crop Science 40(3), 757-764.
| Crossref | Google Scholar |
Bateman NR, Catchot AL, Gore J, et al. (2020) Effects of planting date for soybean growth, development, and yield in the southern USA. Agronomy 10(4), 596.
| Crossref | Google Scholar |
Battisti R, Sentelhas PC, Pascoalino JAL, et al. (2018) Soybean yield gap in the areas of yield contest in Brazil. International Journal of Plant Production 12(3), 159-168.
| Crossref | Google Scholar |
Beza E, Silva JV, Kooistra L, Reidsma P (2017) Review of yield gap explaining factors and opportunities for alternative data collection approaches. European Journal of Agronomy 82, 206-222.
| Crossref | Google Scholar |
Chen Y, Donohue RJ, McVicar TR, Waldner F, Mata G, Ota N, Houshmandfar A, Dayal K, Lawes RA (2020) Nationwide crop yield estimation based on photosynthesis and meteorological stress indices. Agricultural and Forest Meteorology 284, 107872.
| Crossref | Google Scholar |
Corassa GM, Amado TJC, Strieder ML, Schwalbert R, Pires JLF, Carter PR, Ciampitti IA (2018) Optimum soybean seeding rates by yield environment in southern Brazil. Agronomy Journal 110(6), 2430-2438.
| Crossref | Google Scholar |
Couëdel A, Edreira JIR, Pisa Lollato R, Archontoulis S, Sadras V, Grassini P (2021) Assessing environment types for maize, soybean, and wheat in the United States as determined by spatio-temporal variation in drought and heat stress. Agricultural and Forest Meteorology 307, 108513.
| Crossref | Google Scholar |
Faraji A (2014) Evaluation of seed yield and stress tolerance indices in soybean lines and cultivars in Gorgan area. Seed and Plant Production Journal 30(1), 35-45.
| Crossref | Google Scholar |
Filippi P, Whelan BM, Vervoort RW, Bishop TFA (2020) Mid-season empirical cotton yield forecasts at fine resolutions using large yield mapping datasets and diverse spatial covariates. Agricultural Systems 184, 102894.
| Crossref | Google Scholar |
Filippi P, Whelan BM, Bishop TFA (2022) Detecting causes of spatial variation in crop yield with interpretive machine learning. In ‘Proceedings of the 20th Agronomy Australia conference’. (Australian Society of Agronomy). Available at http://agronomyaustraliaproceedings.org/index.php/49-2022/802-2022-technology-modelling-and-crop-s
Gan Y, Stulen I, van Keulen H, Kuiper PJC (2002) Physiological response of soybean genotypes to plant density. Field Crops Research 74(2–3), 231-241.
| Crossref | Google Scholar |
Gao Y, Shi S, Xu M, Cui J (2018) Current research on soybean pest management in China. Oil Crop Science 3(4), 215-227.
| Google Scholar |
Grassini P, Torrion JA, Yang HS, Rees J, Andersen D, Cassman KG, Specht JE (2015a) Soybean yield gaps and water productivity in the western U.S. Corn Belt. Field Crops Research 179, 150-163.
| Crossref | Google Scholar |
Grassini P, van Bussel LGJ, Van Wart J, Wolf J, Claessens L, Yang H, Boogaard H, de Groot H, van Ittersum MK, Cassman KG (2015b) How good is good enough? Data requirements for reliable crop yield simulations and yield-gap analysis. Field Crops Research 177, 49-63.
| Crossref | Google Scholar |
Hajjarpoor A, Kholová J, Pasupuleti J, Soltani A, Burridge J, Degala SB, Gattu S, Murali TV, Garin V, Radhakrishnan T, Vadez V (2021) Environmental characterization and yield gap analysis to tackle genotype-by-environment-by-management interactions and map region-specific agronomic and breeding targets in groundnut. Field Crops Research 267, 108160.
| Crossref | Google Scholar |
Hungria M, Kaschuk G (2014) Regulation of N2 fixation and NO3−/NH4+ assimilation in nodulated and N-fertilized Phaseolus vulgaris L. exposed to high temperature stress. Environmental and Experimental Botany 98, 32-39.
| Crossref | Google Scholar |
Jones EJ, Bishop TFA, Malone BP, Hulme PJ, Whelan BM, Filippi P (2022) Identifying causes of crop yield variability with interpretive machine learning. Computers and Electronics in Agriculture 192, 106632.
| Crossref | Google Scholar |
Krishnan HB, Kim W-S, Oehrle NW, Smith JR, Gillman JD (2020) Effect of heat stress on seed protein composition and ultrastructure of protein storage vacuoles in the cotyledonary parenchyma cells of soybean genotypes that are either tolerant or sensitive to elevated temperatures. International Journal of Molecular Sciences 21(13), 4775.
| Crossref | Google Scholar | PubMed |
Kukal MS, Irmak S (2019) Irrigation-limited yield gaps: trends and variability in the United States post-1950. Environmental Research Communications 1(6), 061005.
| Crossref | Google Scholar |
Kumagai E, Takahashi T (2020) Soybean (Glycine max (L.) Merr.) yield reduction due to late sowing as a function of radiation interception and use in a cool region of Northern Japan. Agronomy 10(1), 66.
| Crossref | Google Scholar |
Lin LI (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics 45, 255-268.
| Google Scholar | PubMed |
Lobell DB, Asner GP (2003) Climate and management contributions to recent trends in U.S. agricultural yields. Science 299(5609), 1032.
| Crossref | Google Scholar | PubMed |
Mansouri Rad A, Nakhzari Moghadam A, Soltani A, Rahemi Karizaki A, Torabi B (2018) Identifying soybean yield-limiting factors by using Comparative Performance Analysis (Case study: Golestan province–Kalaleh). Journal of Crops Improvement 19(4), 1033-1046.
| Crossref | Google Scholar |
Martelloni L, Frasconi C, Fontanelli M, Raffaelli M, Peruzzi A (2016) Mechanical weed control on small-size dry bean and its response to cross-flaming. Spanish Journal of Agricultural Research 14, e0203.
| Crossref | Google Scholar |
Narayanan S, Zoong-Lwe ZS, Gandhi N, Welti R, Fallen B, Smith JR, Rustgi S (2020) Comparative lipidomic analysis reveals heat stress responses of two soybean genotypes differing in temperature sensitivity. Plants 9(4), 457.
| Crossref | Google Scholar | PubMed |
Nehbandani A, Soltani A, Zeinali E, Hoseini F (2017a) Analyzing soybean yield constraints in Gorgan and Aliabad katul using CPA method. Journal of Agroecology 7(1), 109-123.
| Google Scholar |
Nehbandani AR, Soltani A, Zeinali E, Hoseini F, Shahoseini A, Mehmandoy M (2017b) Soybean (Glycine max L. Merr.) yield gap analysis using boundary line method in Gorgan and Aliabad Katul. Journal of Agroecology 9(3), 760-776.
| Google Scholar |
Nehbandani A, Soltani A, Hajjarpoor A, Dadrasi A, Nourbakhsh F (2020a) Comprehensive yield gap analysis and optimizing agronomy practices of soybean in Iran. The Journal of Agricultural Science 158(8-9), 739-747.
| Crossref | Google Scholar |
Nehbandani A, Soltani A, Taghdisi Naghab R, Dadrasi A, Alimagham SM (2020b) Assessing HC27 soil database for modeling plant production. International Journal of Plant Production 14(4), 679-687.
| Crossref | Google Scholar |
Nehbandani A, Soltani A, Nourbakhsh F, Dadrasi A (2020c) Estimating crop model parameters for simulating soybean production in Iran conditions. OCL 27, 58.
| Crossref | Google Scholar |
Nehbandani A, Soltani A, Rahemi-Karizaki A, Dadrasi A, Noubakhsh F (2021) Determination of soybean yield gap and potential production in Iran using modeling approach and GIS. Journal of Integrative Agriculture 20(2), 395-407.
| Crossref | Google Scholar |
Nezamzade E, Soltani A, Dastan S, Ajamnoroozi H (2020) Factors causing yield gap in rape seed production in the eastern of Mazandaran province, Iran. Italian Journal of Agronomy 15(1), 10-19.
| Crossref | Google Scholar |
Pierozan Junior C, Kawakami J, Bridi M, Müller MML, Del Conte MV, Michalovicz L (2015) Phenological and quantitative plant development changes in soybean cultivars caused by sowing date and their relation to yield. African Journal of Agricultural Research 10, 515-523.
| Crossref | Google Scholar |
Rattalino Edreira JI, Mourtzinis S, Conley SP, Roth AC, Ciampitti IA, Licht MA, Kandel H, Kyveryga PM, Lindsey LE, Mueller DS, Naeve SL, Nafziger E, Specht JE, Stanley J, Staton MJ, Grassini P (2017) Assessing causes of yield gaps in agricultural areas with diversity in climate and soils. Agricultural and Forest Meteorology 247, 170-180.
| Crossref | Google Scholar |
Reicosky DC, Allmaras RR (2003) Advances in tillage research in North American cropping systems. Journal of Crop Production 8(1-2), 75-125.
| Crossref | Google Scholar |
Savary S, Willocquet L, Pethybridge SJ, Esker P, McRoberts N, Nelson A (2019) The global burden of pathogens and pests on major food crops. Nature Ecology & Evolution 3(3), 430-439.
| Crossref | Google Scholar | PubMed |
Sentelhas PC, Battisti R, Câmara GMS, Farias JRB, Hampf AC, Nendel C (2015) The soybean yield gap in Brazil–magnitude, causes and possible solutions for sustainable production. The Journal of Agricultural Science 153(8), 1394-1411.
| Crossref | Google Scholar |
Serafin-Andrzejewska M, Helios W, Jama-Rodzeńska A, Kozak M, Kotecki A, Kuchar L (2021) Effect of sowing date on soybean development in South-Western Poland. Agriculture 11(5), 413.
| Crossref | Google Scholar |
Shendryk Y, Davy R, Thorburn P (2021) Integrating satellite imagery and environmental data to predict field-level cane and sugar yields in Australia using machine learning. Field Crops Research 260, 107984.
| Crossref | Google Scholar |
Siahmarguee A, Torabi B, Sohrabi Rad EM, Alimagham SM (2018) Effect of weeds and management factors on soybean yield gap in Kalaleh Township. Journal of Crops Improvement 20(2), 563-576.
| Crossref | Google Scholar |
Soltani A, Alimagham SM, Nehbandani A, et al. (2020) SSM-iCrop2: a simple model for diverse crop species over large areas. Agricultural Systems 182, 102855.
| Crossref | Google Scholar |
Ulzen J, Abaidoo RC, Ewusi-Mensah N, Masso C (2018) On-farm evaluation and determination of sources of variability of soybean response to Bradyrhizobium inoculation and phosphorus fertilizer in northern Ghana. Agriculture, Ecosystems & Environment 267, 23–-32.
| Crossref | Google Scholar |
van Donk SJ, Shaver TM, Petersen JL, Davison DR (2012) Effects of crop residue removal on soil water content and yield of deficit-irrigated soybean. Transactions of the ASABE 55(1), 149-157.
| Crossref | Google Scholar |
van Ittersum MK, Cassman KG, Grassini P, et al. (2013) Yield gap analysis with local to global relevance—a review. Field Crops Research 143, 4–-17.
| Crossref | Google Scholar |
van Oort PAJ, Saito K, Dieng I, Grassini P, Cassman KG, van Ittersum MK (2017) Can yield gap analysis be used to inform R&D prioritisation? Global Food Security 12, 109-118.
| Crossref | Google Scholar |
Zanon AJ, Streck NA, Grassini P (2016) Climate and management factors influence soybean yield potential in a subtropical environment. Agronomy Journal 108(4), 1447–-1454.
| Crossref | Google Scholar |
Zeinali E, Akramghaderi F, Soltani A, Kashiri H (2003) Effect of planting date on yield and yield components of three soybean cultivars in Gorgan. Iranian Journal of Agricultural Science 1, 81–-92.
| Crossref | Google Scholar |
