The crop light temperature yield potential simulation optimization method based on random forest

doi:10.14088/j.cnki.issn0439-8114.2024.08.023

Abstract

Abstract: In order to effectively reduce the amount of data required for crop simulation and improve computing efficiency, a model for estimating the light-temperature yield potential of winter wheat was established based on machine learning. Taking 129 agro-meteorological stations in the winter wheat region of China from 1980 to 2009 as the research object, the characteristic variables of temperature, sunshine hours, latitude and longitude, etc., which had a great influence on the simulation of photoperiod yield potential were selected. Based on the input and output data of WheatGrow model, the random forest model （RF_GS） and the random forest model （RF_Mon） with the variables of growing season and month were established. Finally, the performance of the random forest model was evaluated by root mean square error （RMSE）. The results showed that the random forest model could reduce the data requirement under the premise of ensuring the simulation accuracy, and the accuracy of RF_GS was better than that of RF_Mon. The results of the variable importance test and partial dependence plots showed that latitude, sunshine duration in the growing season, sunshine duration in May and minimum temperature in March had a great influence on photoperiod yield potential simulation. If the range of model validation data exceeded the range of training data, the random forest model’s accuracy could not be guaranteed.

Key words: crop model, WheatGrow model, random forest model, light temperature yield potential, simulation optimization method

CLC Number:

S512.1
S127

XU Hao, SONG Hua-lu, ZHANG Hai-bo, ZHANG Xiao-hu, WANG Shuai. The crop light temperature yield potential simulation optimization method based on random forest[J]. HUBEI AGRICULTURAL SCIENCES, 2024, 63(8): 132-139.

References

[1] 朱艳,汤亮,刘蕾蕾,等.作物生长模型(CropGrow)研究进展[J].中国农业科学,2020,53(16):3235-3256.
[2] ABELEDO L G,SAVIN R,SLAFER G A.Wheat productivity in the Mediterranean Ebro Valley: Analyzing the gap between attainable and potential yield with a simulation model[J].European journal of agronomy,2008,28(4):541-550.
[3] 彭慧文,赵俊芳,谢鸿飞,等.作物模型应用与遥感信息集成技术研究进展[J].中国农业气象,2022,43(8):644-656.
[4] KEATING B A,THORBURN P J.Modelling crops and cropping systems—Evolving purpose, practice and prospects[J]. European journal of agronomy,2018,100:163-176.
[5] MORELL F J,YANG H S,CASSMAN K G,et al.Can crop simulation models be used to predict local to regional maize yields and total production in the U.S. Corn Belt?[J].Field crops research,2016,192:1-12.
[6] 孙少杰,吴门新,庄立伟,等.基于CNN卷积神经网络和BP神经网络的冬小麦县级产量预测[J].农业工程学报,2022, 38(11):151-160.
[7] 甘甜,李雷,李红叶,等.基于多源遥感数据和机器学习算法的冬小麦产量预测研究[J].麦类作物学报,2022, 42(11):1419-1428.
[8] SCHLENKER W H,ROBERTS M J.Nonlinear temperature effects indicate severe damages to US crop yields under climate change[J].Proceedings of the national academy of sciences,2009,106(37):15594-15598.
[9] JEONG J H,RESOP J P,MUELLER N D,et al.Random forests for global and regional crop yield predictions[J].Plos one,2016, 11(6):e0156571.
[10] 牛乾坤,刘浏,黄冠华,等.基于GEE和机器学习的河套灌区复杂种植结构识别[J].农业工程学报,2022,38(6):165-174.
[11] HOFFMAN A L,KEMANIAN A R,FOREST C E.Analysis of climate signals in the crop yield record of sub-Saharan Africa[J].Global change biology,2018,24(1):143-157.
[12] DAI X,HUO Z,WANG H.Simulation for response of crop yield to soil moisture and salinity with artificial neural network[J].Field crops research,2011,121(3):441-449.
[13] BREIMAN L.Random forests[J].Machine learning,2001,45(1):5-32.
[14] EVERINGHAM Y,SEXTON J,SEXTON D,et al.Accurate prediction of sugarcane yield using a random forest algorithm[J].Agronomy for sustainable development,2016,36(2):27.
[15] REICHSTEIN M,CAMPS-VALLS G,STEVENS B,et al.Deep learning and process understanding for data-driven Earth system science[J].Nature,2019,566:195-204.
[16] ZHANG X,XU H,JIANG L,et al.Selection of appropriate spatial resolution for the meteorological data for regional winter wheat potential productivity simulation in China based on WheatGrow model[J].Agronomy,2018,8(10):198.
[17] 吕尊富,刘小军,汤亮,等.基于WheatGrow和CERES模型的区域小麦生育期预测与评价[J].中国农业科学,2013, 46(6):1136-1148.
[18] LIU B,LIU L,ASSENG S,et al.Modelling the effects of heat stress on post-heading durations in wheat: A comparison of temperature response routines[J].Agricultural and forest meteorology,2016,222:45-58.
[19] CAO W,LIU T,LUO W,et al.Simulating organ growth in wheat based on the organ-weight fraction concept[J].Plant production science,2002,5(3):248-256.
[20] 赵扬辉,汤亮,曹卫星,等.小麦生长模拟模型(WheatGrow)的适应性评价[J].麦类作物学报,2010,30(3):443-448.
[21] 肖浏骏,刘蕾蕾,邱小雷,等.小麦生长模型对拔节期和孕穗期低温胁迫响应能力的比较[J].中国农业科学,2021,54(3):504-521.
[22] WATANABE M,SUZUKI T,O’ISHI R,et al. Improved climate simulation by MIROC5: Mean states, variability, and climate sensitivity[J].Journal of climate 2010,23(23):6312-6335.
[23] KONZMANN M,GERTEN D,HEINKE J.Climate impacts on global irrigation requirements under 19 GCMs, simulated with a vegetation and hydrology model[J].Hydrological sciences journal,2013,58(1):88-105.
[24] 文新亚,陈阜.基于DSSAT模型模拟气候变化对不同品种冬小麦产量潜力的影响[J].农业工程学报, 2011,27(S2):74-79.
[25] KURSA M B,RUDNICKI W R.Feature selection with the Boruta package[J].Journal of statistical software,2010,36(11):1-13.
[26] LIAW A,WIENER M.Classification and regression by randomForest[J].R news,2002,2(3):18-22.
[27] VINCENZI S,ZUCCHETTA M,FRANZOI P,et al.Application of a random forest algorithm to predict spatial distribution of the potential yield of Ruditapes philippinarum in the Venice lagoon, Italy[J].Ecological modelling,2011, 222(8):1471-1478.
[28] OSBORNE T,ROSE G,WHEELER T.Variation in the global-scale impacts of climate change on crop productivity due to climate model uncertainty and adaptation[J].Agricultural and forest meteorology,2013,170:183-194.
[29] MCCUEN R H,KNIGHT Z,CUTTER A G.Evaluation of the Nash-Sutcliffe efficiency index[J].Journal of hydrologic engineering,2006,11(6):597-602.
[30] NAGY A,FEHÉR J,TAMÁS J. Wheat and maize yield forecasting for the Tisza river catchment using MODIS NDVI time series and reported crop statistics[J].Computers and electronics in agriculture,2018,151:41-49.
[31] FUKUDA S,SPREER W,YASUNAGA E,et al.Random Forests modelling for the estimation of mango (Mangifera indica L. cv. Chok Anan) fruit yields under different irrigation regimes[J].Agricultural water management,2013,116, 142-150.
[32] HEDDAM S,KISI O.Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree[J].Journal of hydrology,2018,559:499-509.
[33] THORNTON P K,JONES P G,ALAGARSWAMY G,et al.Spatial variation of crop yield response to climate change in East Africa[J].Global environmental change,2009,19(1):54-65.