Iran-Water Resources Research

Iran-Water Resources Research

Simulation of Rainfed Wheat Yield Using Drought Indices by Employing Artificial Neural Network, Random Forest and Support Vector Regression (Case Study: Saqqez City)

Document Type : Original Article

Authors
Mojgan Ahmadi 1
Abbas Kaviani 2
Hadi Ramezani Etedali 2
Alireza Tavakoli 3
1 Department of Water Science and Engineering, Faculty of Agricultural and Natural Resources, Imam Khomeini International University, Qazvin, Iran.
2 Associate Professor, Department of Water Science and Engineering, Faculty of Agricultural and Natural Resources, Imam Khomeini International University, Qazvin, Iran.
3 Associate Professor, Agricultural Engineering Research Institute, Karaj, Iran.
10.22034/iwrr.2023.177606
Abstract
Drought can significantly affect agriculture, especially rainfed agriculture which is highly dependent on precipitation, and thereby threaten the food security and social protection. In this study, the correlation between drought indices, SPI and SPEI, and the rainfed wheat yield was investigated in 5 fields in Saqqez city during the period of 2001-2020 using neural network, random forest, and support vector regression. TRMM precipitation and CRU evapotranspiration were used to calculate the drought indices SPI and SPEI. The AquaCrop model was calibrated with observational data in period 2015-2020 and then each field performance was simulated with the AquaCrop model for the period 2001-2020. The average yield of the fields was evaluated versus the average rainfed wheat yield of the entire Saqqez county and the results showed that the data simulated with the model had a good correlation (R2=0.90) with the latter. In order to investigate the relationship between drought indices and rainfed wheat yield, six scenarios were defined. The results showed that the neural network and random forest method with a significant probability of 95% (P-value=0.0) and an explanatory coefficient of more than 0.70% in train stage, the high value of Nash Sutcliffe index and a small amount of underestimation had a good estimate of the rainfed wheat yield. Also, there is a significant relationship between drought indices, SPI and SPEI, and the rainfed wheat yield in the study area. The results of this research will be useful in managing and planning the development of rainfed wheat cultivation based on the future climatic conditions.
Keywords
Rainfed Wheat Yield
Drought Indices
Random Forest
Artificial Neural Network
Support Vector Machine

Subjects

Alizadeh P, Kamkar B, Shataee S, Kazemi H (2019) Spatial and temporal monitoring of agricultural drought in the wheat cultivated area using Standard Precipitation Index (Case study: West of Golestan Province). Journal of Agroecology 11(3):1069-1084
Breiman L (2001) Random forests. Machine Learning 45:5–32
Brown ME, Lary DJ, Vrieling A, Stathakis D, Mussan H (2008) Neural networks as a tool for constructing continuous NDVI time series from AVHRR and MODIS. The International Journal of Remote Sensing 29:7141–7158
Edwards DC, McKee TB (1997) Characteristics of 20th century drought in the United States at multiple
time scales. Climatology Report Number 97-2, Department of Atmospheric Science, Colorado State
University, Fort Collins
Elbeltagi A, AlThobiani F, Kamruzzaman M, Shaid S, Roy D K, Deb L, Islam M, Kundu PK, Rahman M (2022) Estimating the Standardized Precipitation Evapotranspiration Index using data-driven techniques: A regional study of Bangladesh. Water 14(11):1764
Ghaleni MM, Sharafi S (2022) evaluation of cru ts4.05 and era5 datasets accuracy to precipitation, temperature and potential evapotranspiration in different climates across Iran. Iranian Journal of Irrigation and Drainage 16(5):879-890 (In Persian)
Ghamghami M, Pourmeidani A (2022) Intra-seasonal prediction of irrigated wheat yield using a regional water balance index, (Case study: Qom province). Journal of Agricultural Meteorology 10(1):86-98 (In Persian)
Hosseini SA, Ahmadi H, Houshyar M (2021) Analysis of rainfall system, leading to floods in July 2015 in Saghez City in Kurdistan Province. Journal of Integrated Watershed Management 1(1):47-65 (In Persian)
Hou M, Yao N, Li Y, Liu F, Biswas A, Pulatov A, Hassan I (2022) Better drought index between SPEI and SMDI and the key parameters in denoting drought impacts on spring wheat yields in Qinghai, China. Agronomy 12(7):1552
Jalali M, Mohammadi GH, Hiseini Sadr A, Khoshvaghti H (2017) The role of spatial and temporal fluctuations of climatic parameters in dry land wheat yield (Case study: Kaleibar and Khodaafarin County). Natural Geography Quarterly 9(34):105-123
Karimi H, Zeidali A, OmidiPour R (2018) Evaluation the effect of standard precipitation index on the rainfed wheat yield in Ilam Province. Watershed Engineering and Management 9(4):493-499 (In Persian)
Kaul M, Hill RL, Walthall C (2005) Artificial neural networks for corn and soybean yield prediction. Agricultural Systems 85(1):1–18
Khalili N, Davary K, Alizadeh A, Kafi M, Ansari H (2015) Simulation of rainfed wheat yield using AquaCrop Model, Case study: Researches Station Northern Khorasan. Journal of Water and Soil 28(5):930-939
Kushwaha N L, Rajput J, Elbeltagi A, Elnaggar A Y, Sena D R, Vishwakarma D K, Mani I, Hussein EE (2021) Data intelligence model and meta-heuristic algorithms-based pan evaporation modelling in two different agro-climatic zones: A case study from Northern India. Atmosphere 12(12):1654
Li L, Wang B, Feng F, Liu D.L, He Q, Zhang Y, Wang Y, Li S, Lu X, Yue C, Li Y, He J, Feng H, Yang G, Yu Q (2022) Developing machine learning models with multi-source environmental data to predict wheat yield in China. Computers and Electronics in Agriculture 194:1680-1699
Manzano A, Clemente M A, Morata A, Luna M Y, Beguería S, Vicente-Serrano S M, Martín M L (2019) Analysis of the atmospheric circulation pattern effects over SPEI drought index in Spain. Atmospheric Research 230:104630
Maughan N, Camenisch C, Brázdil R, White S (2022) Societal impacts of historical droughts in a warming world. Regional Environmental Change 22:74
McKee T B, Doesken N J, Kleist J (1993) The relationship of drought frequency and duration to time scale. In Proceedings of the Eighth Conference on Applied Climatology, Anaheim, CA, USA, 17–22 January 1993; pp. 17–22
Mohammed S, Alsafadi K, Enaruvbe G O, Bashir B, Elbeltagi A, Széles A, Alsalman A, Harsanyi E (2022) Assessing the impacts of agricultural drought (SPI/SPEI) on maize and wheat yields across Hungary. Scientific Reports 12:8838
Morsy M, Moursy F I, Sayad T, Shaban S (2022) Climatological study of SPEI Drought Index using observed and CRU gridded dataset over Ethiopia. Pure and Applied Geophysics 179:3055–3073
Mottaleb K A, Gumma M, Mishra A, Mohanty S (2015) Quantifying production losses due to drought and submergence of rainfed rice at the household level using remotely sensed MODIS data. Agricultural Systems 137:227-235
Panahi S, Samadianfard S, Nazemi AH (2022) Modeling the yield of rain-fed wheat, barley and alfalfa product using support vector regression and genetic programming. Water and Soil Science 32(2):97-111
Sheskin D (2007) Handbook of parametric and nonparametric statical procedures. Chapman&Hall/CRC,1737 pp
Smola AJ, Schölkopf BA (2004) A tutorial on support vector regression. Statistics and Computing 14:199–222
Teimouri M, Gholami V, Khalegi MR (2023) Assesment of drought impacts on rainfed wheat yield using SPI and Agricultural-SPI indices (Case study: North Khorasan province). Journal of Agriculture Meteorology 10(2):17-27
 Tian L, Yuan S, Quiring S M (2018) Evaluation of six indices for monitoring agricultural drought in the South-Central United States. Agricultural and Forest Meteorology 249:107–119
Tirivarombo S, Osupile D, Eliasson P (2018) Drought monitoring and analysis: Standardised Precipitation Evapotranspiration Index (SPEI) and Standardised Precipitation Index (SPI). Physics and Chemistry of the Earth 106:1–10
Vicente-Serrano S M, Beguería S, López-Moreno JI (2010) A multiscalar drought index sensitive to global warming: The Standardized Precipitation Evapotranspiration Index. Journal of Climate 23:1696–1718
Wang H, Vicente-serrano S M, Tao F, Zhang X, Wang P, Zhang C, Chen Y, Zhu D, Kenawy A (2016) Monitoring winter wheat drought threat in northern China using multiple climate-based drought indices and soil moisture during 2000–2013. Agricultural and Forest Meteorology 228–229:1–12
Wilhite DA (2005) Drought and water crises: Science, technology, and management issues. Crc Press
Yue J, Feng H, Yang G, & Li Z (2018) A comparison of regression techniques for estimation of above-ground winter wheat biomass using near-surface spectroscopy. Remote Sensing 10(1):66
Zangeneh Inaloo M, Ghahraman B, Faridhoseini A (2023) Evaluation of the accuracy of TRMM satellite for estimating precipitation and runoff values in Shapour River Basin in Fars Province. Iranian Journal of Irrigation and Drainage 13(1):203-216
Zarei AB, Shabani A, Moghimi MM (2021) Accuracy assessment of the SPEI, RDI and SPI drought indices in regions Iran with different climate conditions. Pure and Applied Geophysics 178:1387-1403

  • Receive Date 25 April 2023
  • Revise Date 01 August 2023
  • Accept Date 21 August 2023