Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Applications of Machine Learning Algorithms in Nitrogen Fertilizer Management of Triticale


Affiliations
1 Department of Soil Science and Plant Nutrition, Faculty of Agriculture, Eskisehir Osmangazi University, Eskisehir, Turkey
2 Department of Field Crops, Faculty of Agriculture, Eskisehir Osmangazi University, Eskisehir, Turkey
3 Department of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Eskisehir Osmangazi University, Eskisehir, India
 

In this study, a new classification technique is proposed to distinguish the appropriate one from four different nitrogen (N) fertilizer doses (0, 40, 80, and 160 kg ha−1) using six triticale cultivars. In the classification phase, nine yield featuresfrom 30 plants of the same cultivar were measured, that is, each dose or class has 30 feature vectors consisting of ninefeatures. Next, six triticale cultivars were classified for each dose of N fertilizer separately by using 30 feature vectorsbelonging to each dose. Similarly, the same classification task was repeated by using all feature vectors taken from fourdoses of N fertilizer. What makes this study novel is the classification process of six triticale cultivars by taking into accounttheir characters based on different doses of N fertilizer. The classification tasks were conducted by applying CommonVector Approach, Support Vector Machine, k-Nearest Neighbor, and Decision Trees algorithms. While satisfactory resultswere obtained from the training sets for all cases, the test set accuracy is relatively lower for the classification of four dosesof N fertilizer and six cultivars since features extracted from different doses of N fertilizer for the same cultivar are close toeach other. Furthermore, the number of feature vectors is insufficient to classify classes efficiently. Interestingly, when thecommon information of the classifiers was extracted with the biplot technique, useful results were obtained in selectingappropriate N doses for several triticale varieties. Combined with the results of future comprehensive studies, applicableresults for the agricultural sector can be proposed.

Keywords

Cereals, Common vector approach, K-Nearest neighbor, Plant nutrition, Support vector machine.
User
Notifications
Font Size

  • Mergoum M, Sapkota S, El Doliefy A E A, Naraghi S M, Pirseyedi S, Alamri M S & Abu Hammad W, Triticale (x TriticosecaleWittmack) Breeding, Adv Plant Breeding Strat: Cereals, 5 (2019) 405-451, https://doi.org/10.1007/978-3-030-23108-8_11.

  • de Oliveira S A, Ciampitti I A, Slafer G A & Lollato R P, Nitrogen utilization efficiency in wheat: A global perspective, Europ J Agr, 114 (2020) 126008, https://doi.org/10.1016/j.eja.2020.126008.

  • Omara P, Aula L, Oyebiyi F & Raun W R, World cereal nitrogen use efficiency trends: review and current knowledge, Agrosys, Geosci Environ, 2(1) (2019) 1–8, https://doi.org/10.2134/age2018.10.0045.

  • Martínez-Dalmau J, Berbel J & Ordóñez-Fernández R, Nitrogen fertilization-A review of the risks associated with the in efficiency of its use and policy responses, Sustainability, 13(10) (2021) 5625, https://doi.org/10.3390/su13105625.

  • Yu X, Keitel C, Zhang Y, Wangeci A N & Dijkstra F A, Global meta-analysis of nitrogen fertilizer use efficiency in rice, wheat and maize, Agric Ecosyst Env, 338 (2022) 108089, https://doi.org/10.1016/j.agee.2022.108089.

  • Koutroubas S D, Fotiadis S & Damalas C A, Grain yield and nitrogen dynamics of Mediterranean barley and triticale, Arch Agric Soil Sci, 62(4) (2016) 484-501, https://doi.org/10.1080/03650340.2015.1064902.

  • Malik A H, Andersson A, Kuktaite R, Mujahid M Y, Khan B & Johansson E, Genotypic variation in dry weight and nitrogen concentration of wheat plant parts; relations to grain yield and grain protein concentration, J Agric Sci, 4(11) (2012) 11, http://dx.doi.org/10.5539/jas.v4n11p11.

  • Liu J, Cai H, Chen S, Pi J & Zhao L, A review on Soil Nitrogen Sensing Technologies: Challenges, Progress and Perspectives, Agriculture, 13(4) (2023) 743, https://doi.org/10.3390/agriculture13040743.

  • Garg R, Aggarwal H, Centobelli P & Cerchione R, Extracting knowledge from big data for sustainability: A comparison of machine learning techniques, Sustainability, 11(23) (2019) 6669, https://doi.org/10.3390/su11236669.

  • Olgun M, Onarcan A O, Ozkan K, Isık S, Sezer O, Ozgisi K, Ayter N G, Basciftci Z B, Ardıc M & Koyuncu O, Wheat grain classification by using dense SIFT features with SVM classifier, Comput Electron Agric, 122 (2016) 185–190, https://doi.org/10.1016/j.compag.2016.01.033.

  • Naresh V, Vatsala B R & Vidya C R, Crop yield prediction and fertilizer recommendation, Int J Eng Sci Comp, 10(6) (2020) 26256–26258, https://doi.org/10.1109/CSNT57126.2023.10134662.

  • Manoj Kumar D P, Malyadri N & Srikanth M S, A machine learning model for crop and fertilizer recommendation, Nveo-Nat Vol Essent Oils J, 8(5) (2021)10531–10539.

  • Aytac Z, Gulmezoglu N & Gulmezoglu M B, Application of the common vector approach on identification of winter rapeseed (Brassica napus L.) cultivars and their yield characters, Int J Sustain Agric Manag Inform, 2(1) (2016) 66–78, https://doi.org/10.1504/IJSAMI.2016.077271.

  • Khan A, Vibhute A D, Mali S & Patil C H, A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications, Ecol Inform, 69 (2022) 101678, https://doi.org/10.1016/j.ecoinf.2022.101678.

  • Zapotoczny P, Discrimination of wheat grain varieties using image analysis: morphological features, Eur Food Res Technol, 233 (2011) 769–779, https://doi.org/10.1007/s00217-011-1573-y.

  • Romero J R, Roncallo P F, Akkiraju P C, Ponzoni I, Echenique V C & Carballido J A, Using classification algorithms for predicting durum wheat yield in the province of Buenos Aires, Comput Electron Agric, 96 (2013) 173–179, https://doi.org/10.1016/j.compag.2013.05.006.

  • Onarcan A O, Ozkan K & Olgun M, Unclassified wheat identification with bag of contour fragments, In Signal Processing and Communications Applications Conference (IEEE) 2017, 1–4, doi: 10.1109/SIU.2017.7960305.

  • Bondre D A & Mahagaonkar S, Prediction of crop yield and fertilizer recommendation using machine learning algorithms, Int J Eng Appl Sci Technol, 4(5) (2019) 371–376.

  • Meng L, Liu H L, Ustin S & Zhang X, Predicting maize yield at the plot scale of different fertilizer systems by multi-source data and machine learning methods, Remote Sens, 13(18) (2021) 3760, https://doi.org/10.3390/rs13183760.

  • Gulmezoglu M B, Keskin M, Dzhafarov V & Barkana A, A novel approach to isolated word recognition, IEEE Trans Speech Audio Process, 7(6) (1999) 620–628, doi: 10.1109/89.799687.

  • Gulmezoglu M B, Dzhafarov V & Barkana A, The common vector approach and its relation to principal component analysis, IEEE Trans Speech Audio Process, 9(6) (2001) 655–662, doi: 10.1109/89.943343.

  • Gulmezoglu M B, Dzhafarov V, Edizkan R & Barkana A, The common vector approach and its comparison with other subspace methods in case of sufficient data, Comput Speech Lang, (21)2 (2007) 266–281, https://doi.org/10.1016/j.csl.2006.06.002.

  • Oja E, Subspace methods of pattern recognition (John Wiley and Sons, Inc., New York) 1983.

  • Hotta K, Support vector machine with local summation kernel for robust face recognition, In: Proc. of 17th Int. Conf. on Pattern Recognition (IEEE) 2004, 482–485, doi: 10.1109/ICPR.2004.1334571.

  • Vapnik V, The nature of statistical learning theory, Statistics for Engineering and Information Science (Springer Verlag, Berlin) 2000.

  • Cevikalp H, Yavuz H S, Edizkan R, Gunduz H & Kandemir C M, Comparisons of features for automatic eye and mouth localization, In: Proc. of the IEEE Int Symp on Innovations in Intelligent Systems and Applications (IEEE) 2011, 576–580, doi: 10.1109/INISTA.2011.5946152.

  • Burges C J C, Tutorial on support vector machines for pattern recognition, Data Min Knowl Discov, 2 (1998) 121–167, https://doi.org/10.1023/A:1009715923555.

  • Duin R P W, Juszczak P, Paclik P, Pekalska E, De Ridder D & Tax D M J, PRTools4, A Matlab tool box for pattern recognition (Delft University of Technology) 2004.

  • Cunningham P & Delany S J, k-Nearest neighbour classifiers, Mult Class Syst, 34 (2007) 1–17, https://doi.org/10.1145/3459665.

  • Darooei R, Sanadgol G, Gh-Nataj A, Almasnia M, Darivishi A, Eslaminejad A & Raoufy M R, Discriminating tuberculous pleural effusion from malignant pleural effusion based on routine pleural fluid biomarkers, using mathematical methods, Tanaffos, 16(2) (2017) 157.

  • Gulmezoglu M B & Gulmezoglu N, Classification of bread wheat varieties and their yield characters with the common vector approach, International Conference on Chemical, Environmental and Biological Sciences (Dubai, BAE) 2015, 142–145.

  • Kutlu I, Heritability of end-use quality and biofortification characteristics in line x tester bread wheat (Triticum aestivum L.) crosses, Appl Ecol Environ Res, 16(5) (2018) 7305–7326, http://dx.doi.org/10.15666/aeer/1605_73057326.

  • Kutlu I, Gulmezoglu M B & Karaduman Y, Classifying wheat genotypes using machine learning models for single kernel characterization system measurements, J Sci Ind Res, 80 (2021) 985–991, 10.56042/jsir.v80i11.40757.

  • Irfan S A, Azeem B, Irshad K, Algarni S, KuShaari K, Islam S & Abdelmohimen M A, Machine learning model for nutrient release from biopolymers coated controlled-release fertilizer, Agriculture, 10(11) (2020) 538, https://doi.org/10.3390/agriculture10110538.

  • Agarwal S & Tarar S, A hybrid approach for crop yield prediction using machine learning and deep learning algorithms, In J Phy: Conference Series, IOP Publishing, 1714(1) (2021) 012012, https://doi.org/10.1088/ 1742-6596/1714/1/012012.


Abstract Views: 27

PDF Views: 22




  • Applications of Machine Learning Algorithms in Nitrogen Fertilizer Management of Triticale

Abstract Views: 27  |  PDF Views: 22

Authors

Nurdilek Gulmezoglu
Department of Soil Science and Plant Nutrition, Faculty of Agriculture, Eskisehir Osmangazi University, Eskisehir, Turkey
Imren Kutlu
Department of Field Crops, Faculty of Agriculture, Eskisehir Osmangazi University, Eskisehir, Turkey
M. Bilginer Gulmezoglu
Department of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Eskisehir Osmangazi University, Eskisehir, India

Abstract


In this study, a new classification technique is proposed to distinguish the appropriate one from four different nitrogen (N) fertilizer doses (0, 40, 80, and 160 kg ha−1) using six triticale cultivars. In the classification phase, nine yield featuresfrom 30 plants of the same cultivar were measured, that is, each dose or class has 30 feature vectors consisting of ninefeatures. Next, six triticale cultivars were classified for each dose of N fertilizer separately by using 30 feature vectorsbelonging to each dose. Similarly, the same classification task was repeated by using all feature vectors taken from fourdoses of N fertilizer. What makes this study novel is the classification process of six triticale cultivars by taking into accounttheir characters based on different doses of N fertilizer. The classification tasks were conducted by applying CommonVector Approach, Support Vector Machine, k-Nearest Neighbor, and Decision Trees algorithms. While satisfactory resultswere obtained from the training sets for all cases, the test set accuracy is relatively lower for the classification of four dosesof N fertilizer and six cultivars since features extracted from different doses of N fertilizer for the same cultivar are close toeach other. Furthermore, the number of feature vectors is insufficient to classify classes efficiently. Interestingly, when thecommon information of the classifiers was extracted with the biplot technique, useful results were obtained in selectingappropriate N doses for several triticale varieties. Combined with the results of future comprehensive studies, applicableresults for the agricultural sector can be proposed.

Keywords


Cereals, Common vector approach, K-Nearest neighbor, Plant nutrition, Support vector machine.

References