Prediction of spring and summer maize yield in China based on feature analysis and hybrid DHKELM algorithms
DOI:
https://doi.org/10.25165/ijabe.v18i6.9749Keywords:
yield, feature analysis algorithm, deep hybrid kernel extreme learning machine, maize, Chaos game optimizationAbstract
Crop yield prediction helps to enhance the stability of agricultural product supply and promote sustainable agricultural development, both of which are crucial for food production and security. To develop simple yet highly accurate crop yield prediction models, this study proposed a spring- and summer-maize yield prediction model based on the deep hybrid kernel extreme learning machine (DHKELM) algorithm. In this study, four tree-based feature importance analysis algorithms, including classification and regression tree, gradient boosting decision tree, random forest, and extreme gradient boosting algorithms, were utilized to analyze the importance of the factors affecting the yield of spring and summer maize. Then, based on the analysis of the four algorithms, different combinations of factors were established to obtain the optimal combination of features. Moreover, to improve the prediction accuracy of the machine learning model, this study utilized three optimization algorithms, including the bald eagle search algorithm, chaos game optimization (CGO) algorithm, and carnivorous plant algorithm, to optimize the hyperparameters in the DHKELM algorithm. The results of the study showed that planting density and plant height were important factors affecting maize yield, and net solar radiation (Rn) received during the reproductive period exhibited the highest relative importance. Appropriate feature combinations can effectively improve model prediction accuracy. The optimal feature combination for spring maize included planting density, plant height, Rn, mean temperature (Tmean), minimum temperature (Tmin), and cumulative temperature, and the optimal feature combination for summer maize included Rn, plant height, planting density, Tmin, and Tmean. Among the three optimization algorithms, the CGO algorithm exhibited the best optimization effect and could significantly improve the prediction accuracy of the DHKELM algorithm. When the optimal combination of features was used as input, the CGO–DHKELM model used for maize yield prediction provided the following values: RMSE=1.488 t/hm2, R2=0.862, MAE=1.051 t/hm2, and NSE=0.852 for spring maize; RMSE=1.498 t/hm2, R2=0.892, MAE=1.055 t/hm2, and NSE=0.891 for summer maize. Thus, the findings of the study provide a reference for high-precision prediction of spring and summer maize yields in China. Key words: yield; feature analysis algorithm; deep hybrid kernel extreme learning machine; maize; Chaos game optimization DOI: 10.25165/j.ijabe.20251806.9749 Citation: Zhao L, Wang F, Xu Z Z, Meng D, Qing S H, Chen S C, et al. Prediction of spring and summer maize yield in China based on feature analysis and hybrid DHKELM algorithms. Int J Agric & Biol Eng, 2025; 18(6): 191–201.References
Han J C, Zhang Z, Cao J, Luo Y C, Zhang L L, Li Z Y, et al. Prediction of winter wheat yield based on multi-source data and machine learning in China. Remote Sensing, 2020; 12(2): 236.
Cheng M H, Penuelas J, McCabe M F, Atzberger C, Jiao X Y, Wu W B, et al. Combining multi-indicators with machine-learning algorithms for maize yield early prediction at the county-level in China. Agricultural and Forest Meteorology, 2022; 323: 109057.
Li M Y, Zhao J, Yang X G. Building a new machine learning-based model to estimate county-level climatic yield variation for maize in Northeast China. Computers and Electronics in Agriculture, 2021; 191: 106557.
Geipel J, Link J, Claupein W. Combined spectral and spatial modeling of corn yield based on aerial images and crop surface models acquired with an unmanned aircraft system. Remote Sensing, 2014; 6(11): 10335–10355.
Zhao Y X, Xiao D P, Bai H Z, Tang J Z, Liu D L, Qi Y Q, et al. The prediction of wheat yield in the North China Plain by coupling crop model with machine learning algorithms. Agriculture, 2022; 13(1): 99.
Tao F, Palosuo T, Rötter R P, Díaz-Ambrona C G H, Mínguez M I, Semenov M A, et al. Why do crop models diverge substantially in climate impact projections? A comprehensive analysis based on eight barley crop models. Agricultural and Forest Meteorology, 2020; 281: 107851.
Berghuijs H N C, Silva J V, Reidsma P, de Wit A J W. Expanding the WOFOST crop model to explore options for sustainable nitrogen management: A study for winter wheat in the Netherlands. European Journal of Agronomy, 2024; 154: 127099.
Gautam V, Gani A, Pathak S, Shukla A K. Evaluating crop yield prediction models in illinois using aquacrop, semi-physical model and artificial neural networks. Scientific Reports, 2025; 15(1): 27494.
Xu X B, He W, Zhang H Y. Random hierarchical model for estimation of wheat yield in the North China Plain at different spatial scales. Field Crops Research, 2024; 306: 109226.
Ren Y T, Li Q Z, Du X, Zhang Y, Wang H Y, Shi G W, et al. Analysis of corn yield prediction potential at various growth phases using a process-based model and deep learning. Plants, 2023; 12(3): 446.
Kheir A M S, Mkuhlani S, Mugo J W, Elnashar A, Nangia V, Deware M, et al. Integrating APSIM model with machine learning to predict wheat yield spatial distribution. Agronomy Journal, 2023; 115(6): 3188–3196.
Meng X, Hou Q Z, Quan L M, Qiao J F. Self-organizing fuzzy neural network with adaptive evolution strategy for nonlinear and nonstationary processes. Artificial Intelligence Review, 2025; 58(9): 280.
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541), Budapest, Hungary: IEEE, 2004; pp.985–990.
Huang G, Huang G B, Song S J, You K Y. Trends in extreme learning machines: A review. Neural Networks, 2015; 61: 32–48.
Huang J C, Ko K M, Shu M H, Hsu B M. Application and comparison of several machine learning algorithms and their integration models in regression problems. Neural Computing and Applications, 2020; 32(10): 5461–5469.
Jiang X F, Duan H C, Liao J, Guo P L, Huang C H, Xue X. Estimation of soil salinization by machine learning algorithms in different arid regions of Northwest China. Remote Sensing, 2022; 14(2): 347.
Ji J T, Li N N, Cui H W, Li Y C, Zhao X B, Zhang H L, et al. Study on monitoring spad values for multispatial spatial vertical scales of summer maize based on UAV multispectral remote sensing. Agriculture, 2023; 13(5): 1004.
Hai M W, Wang M, Zhou B, Zhang Q. Assessment of frost heave in coarse-grained soil: A novel application of multi-strategy enhanced dung beetle-optimized KELM model. Earth Science Informatics, 2025; 18(1): 63.
Cheng Y H, Hu B B. Forecasting regional carbon prices in China based on secondary decomposition and a hybrid kernel-based extreme learning machine. Energies, 2022; 15(10): 3562.
Ahmad F, Javed K, Tahir A, Khan M U G, Abbas M, Rabbani M, et al. Identifying key soil characteristics for Francisella tularensis classification with optimized machine learning models. Scientific Reports, 2024; 14(1): 1743.
Zhao L, Qing S H, Li H, Qiu Z M, Niu X L, Shi Y, et al. Estimating maize evapotranspiration based on hybrid back-propagation neural network models and meteorological, soil, and crop data. International Journal of Biometeorology, 2024; 68(3): 511–525.
Alsattar H A, Zaidan A A, Zaidan B B. Novel meta-heuristic bald eagle search optimisation algorithm. Artificial Intelligence Review, 2020; 53: 2237–2264.
Huang Y. Improved SVM-based soil-moisture-content prediction model for tea plantation. Plants, 2023; 12(12): 2309.
Talatahari S, Azizi M. Chaos game optimization: a novel metaheuristic algorithm. Artificial Intelligence Review, 2021; 54(2): 917–1004.
He Y C, Yang K, Wang X Q, Huang H S, Chen J D. Quality prediction and parameter optimisation of resistance spot welding using machine learning. Applied Sciences, 2022; 12(19): 9625.
Ong K M, Ong P, Sia C K. A carnivorous plant algorithm for solving global optimization problems. Applied Soft Computing, 2021; 98: 106833.
Wang Y, Wang W, Chen Y. Carnivorous plant algorithm and BP to predict optimum bonding strength of heat-treated woods. Forests, 2022; 14(1): 51.
Zhao L, Qing S H, Bai J Y, Hao H H, Li H, Shi Y, et al. A hybrid optimized model for predicting evapotranspiration in early and late rice based on a categorical regression tree combination of key influencing factors. Computers and Electronics in Agriculture, 2023; 211: 108031. doi: 10.1016/j.compag.2023.108031.
Peng S R, Guo L J, Li Y S, Huang H Y, Peng J Y, Liu X X. Biogas production prediction based on feature selection and ensemble learning. Applied Sciences, 2024; 14(2): 901.
Fei H, Fan Z H, Wang C K, Zhang N N, Wang T, Chen R G, et al. Cotton classification method at the county scale based on multi-features and random forest feature selection algorithm and classifier. Remote Sensing, 2022; 14(4): 829.
Peng Y P, Wang L, Zhao L, Liu Z H, Lin C J, Hu Y M, et al. Estimation of soil nutrient content using hyperspectral data. Agriculture, 2021; 11(11): 1129.
Mohammadi B, Mehdizadeh S. Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm. Agricultural Water Management, 2020; 237: 106145.
Zheng H F, Chen L D, Han X Z, Zhao X F, Ma Y. Classification and regression tree (CART) for analysis of soybean yield variability among fields in Northeast China: The importance of phosphorus application rates under drought conditions. Agriculture, Ecosystems & Environment, 2009; 132(1–2): 98–105.
Gill M, Anderson R, Hu H F, Bennamoun M, Petereit J, Valliyodan B, et al. Machine learning models outperform deep learning models, provide interpretation and facilitate feature selection for soybean trait prediction. BMC plant biology, 2022; 22(1): 180.
Dastres E, Rabiei-Dastjerdi H, Esmaeili H, Amiri M, Sonboli A, Mirjalili M H. Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using innovative hybrid machine learning algorithms. Environmental and Sustainability Indicators, 2025; 26: 100694.
Cheng E H, Zhang B, Peng D L, Zhong L H, Yu L, Liu Y, et al. Wheat yield estimation using remote sensing data based on machine learning approaches. Frontiers in Plant Science, 2022; 13: 1090970.
Baloch N, Liu W M, Hou P, Ming B, Xie R Z, Wang K R, et al. Effect of latitude on maize kernel weight and grain yield across China. Agronomy Journal, 2021; 113(2): 1172–1182.
Ustuner M, Simsek F F. An assessment of training data for agricultural land cover classification: a case study of Bafra, Türkiye. Earth Science Informatics, 2025; 18(1): 7.
Miao H L, Zhang R, Song Z H, Chang Q R. Estimating winter wheat canopy chlorophyll content through the integration of unmanned aerial vehicle spectral and textural insights. Remote Sensing, 2025; 17(3): 406.
Lv L, Wang W H, Zhang Z Y, Liu X G. A novel intrusion detection system based on an optimal hybrid kernel extreme learning machine. Knowledge-based systems, 2020; 195: 105648.
Fu J C, Song Z X, Meng J H, Wu C L. Prediction of lithium-ion battery state of health using a deep hybrid kernel extreme learning machine optimized by the improved black-winged kite algorithm. Batteries, 2024; 10(11): 398.
Wang S L, Guo X L, Sun T L, Xu L H, Zhu J F, Li Z C, et al. Short-term photovoltaic power forecasting based on the VMD-IDBO-DHKELM model. Energies, 2025; 18(2): 403.
Wang Y G, Yu Y D, Ma Y C, Shi J. Lithium-ion battery health state estimation based on improved snow ablation optimization algorithm-deep hybrid kernel extreme learning machine. Energy, 2025; 323: 135772.
Hou H P, Ma W, Noor M A, Tang L Y, Li C F, Ding Z S, et al. Quantitative design of yield components to simulate yield formation for maize in China. Journal of Integrative Agriculture, 2020; 19(3): 668–679.
Luo S Z, Liu W W, Zhang Y Q, Wang C, Xi X H, Nie S, et al. Maize and soybean heights estimation from unmanned aerial vehicle (UAV) LiDAR data. Computers and Electronics in Agriculture, 2021; 182: 106005.
Liu Q, Yang Z P, Zhou W, Wang T, Fu Y, Yue X P, et al. Solar radiation utilization of five upland–paddy cropping systems in low-light regions promoted by diffuse radiation of paddy season. Agricultural and Forest Meteorology, 2023; 338: 109527.
Zhou N B, Zhang J, Fang S L, Wei H Y, Zhang H C. Effects of temperature and solar radiation on yield of good eating-quality rice in the lower reaches of the Huai River Basin, China. Journal of Integrative Agriculture, 2021; 20(7): 1762–1774.
Gao Z, Feng H Y, Liang X G, Zhang L, Lin S, Zhao X, et al. Limits to maize productivity in the North China Plain: A comparison analysis for spring and summer maize. Field Crops Research, 2018; 228: 39–47.
Chen C, Pang Y M. Response of maize yield to climate change in Sichuan province, China. Global Ecology and Conservation, 2020; 22: e00893.
Hou P, Liu Y E, Xie R Z, Ming B, Ma D L, Li S K, et al. Temporal and spatial variation in accumulated temperature requirements of maize. Field Crops Research, 2014; 158: 55–64.
Talatahari S, Azizi M. Optimization of constrained mathematical and engineering design problems using chaos game optimization. Computers & Industrial Engineering, 2020; 145: 106560.
Zhang P L, Sun X B, Wang J Q, Song H H, Bei J L, Zhang H Y. The discrete carnivorous plant algorithm with similarity elimination applied to the traveling salesman problem. Mathematics, 2022; 10(18): 3249.
Wu J H, Hu Y, Wu D Q, Yang Z Y. An aquatic product price forecast model using VMD-IBES-LSTM hybrid approach. Agriculture, 2022; 12(8): 1185.
Downloads
Published
How to Cite
Issue
Section
License
IJABE is an international peer reviewed open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
