N

Save Nature to Survive

15(2): 149-155, 2020
www.thebioscan.com

SEASONAL CROP YIELD FORECASTING METHODS,

FORECASTING-METHODS,
ACCURACIES
CCURACIES AND LIMIT ATIONS
LIMITATIONS:: A REVIEW

M. HANUMANTHAPPA1., VIGNESH*2., A. T. KRISHNAMURTHY 3AND REKHA BADALINGAPPANAVAR4

1
COH, Mudigere - 577 132 , Karnataka
2
UAHS, Shivamogga - 577 216, Karnataka
3
Agricultural Extension, COH, Mudigere - 577 132, Karnataka
4
Agronomy, COH, Mudigere - 577 132, Karnataka
e-mail: vignesh.shivappa@gmail.com

KEYWORDS ABSTRACT
Forecasting Accurate crop yield forecasting helps the government to formulate sound policies related to import and exports,
Statistical models allocation of food grains and price setting. Similarly, the traders and industries can make decisions regarding
Simulation models business activities like wages, purchase of raw materials and working hours. Crop management practices can be
Accuracies standardized to get maximum yield to reduce the pre and post harvest losses of produce. The impact of climate
change on the crops can also be known. This forecasting can be done using different techniques like statistical
Received on : models and crop simulation models. The information of weather, plant characters, environment, remote
24.04.2020 sensors etc. can be used as input data for forecasting. It can be concluded that forecasting the crop yield near the
harvest is more accurate, with r2= 0.7-0.8 being predominant than at the early stages (r2=0.5-0.6). Further
Accepted on : improvement in the accuracy in forecasting is possible with the use of artificial intelligence and machine learning.
25.05.2020

*Corresponding
author

INTRODUCTION system, disaster relief, and storage can be planned better.

Traders can decide the purchase of crop yield; fix the laborers’
Agriculture is the backbone of the Indian economy. It is gifted working hours, and their wages and the sales. The impact of
with varied soil and climatic resources, which enables the climate change and different crop management practices can
production of different crops. India is one of the major be assessed by changing the weather parameters, date of
producing countries of various crops. Therefore, forecasting sowing, fertilizers, spacing, irrigation and so on
the yield has many benefits. Predicting the yield of the crop (Hanumanthappa et al., 2016a). Suitability of varieties to
within the season prior before its harvest is known as yield different locations can be tested, thereby reducing the time
forecasting. The top 10 countries where yield forecast is and resources involved in multi location trails. Overall, the
implemented are the United States, India, Canada, China, food security of the nation and the price fluctuation can be
Spain, Germany, Australia, United Kingdom, Italy and France managed.
(Fig. 1). Thompson (1969) was the first to forecast the yield of
Many scientists have used different methods of forecasting in
corn by regressing the average regional yields with the weather
various crops to date. The review is done to summarize some
to generate a general trend in the former Soviet Union. The
of those and know the possible future works.
biotic and abiotic factors like pests and genetics of the crop,
soils and climate (temperature, relative humidity, wind, rainfall
and solar radiation) affect the yield of the crops MATERIALS AND METHODS
(Hanumanthappa et al., 2016a). These factors are taken as
input parameters in yield forecasting models. Weather data is
Methods of crop yield forecasting
recorded according to the standard meteorological weeks
(SMW) i.e. first week of crop season to last week of crop season. Basso and Liu (2018) classified the forecasting methods region
All the weather data used in the models are weekly average. In wise (Fig. 2). It can be seen that globally, remote sensing data
contrast, the rainfall is taken as a weekly summation. is used in more than 50 percent of the papers.
India stands second in the forecasting of yield. Forecasting Agrometeorological data follow this. A similar trend is observed
provides ample time for policymakers to formulate suitable Table 1: Methods of yield forecasting.
policies. By comparing the forecasted supply with the demand, Method of forecasting Selected references
1.Statistical models using
import and export related decisions can be made. With the a)Meteorological inputs. Murata (1975); Sreenivasan and Banerjee (1978).
help of a demand-supply schedule, prices of the grains can b)Sensor based inputs. Erdle et al. (2011); Bannari et al. (1995).
be fixed. Allocation of food grains to the public distribution 2.Crop simulation models Asseng et al. (2014); Basso et al. (2016).

149
M. HANUMANTHAPPA et al.,

in Asia, Africa and Americas. In Oceania, there is the use of (crop yield) is done. Ranjan et al. (2012) developed regression
agro-meteorological data in many of the papers, followed by equations for yield prediction of Wheat using remote sensing
remote sensing. In Europe, both the data are used equally. and meteorological data. Dharmaraja et al. (2019) forecasted
Use of Sensors in crop yield forecasting the yield of Bajra by linear regression and time series models.
Gupta et al. (2018) developed different statistical models using
Each crop has a specific heat signature and this signature is
weather variables for different U.P. districts to forecast mustard
detected by using sensors. Satellites like SPOT Vegetation,
yield. Sawa and Ibrahim (2011) studied the impact of different
AVHRR, LANDSAT, MODIS, Radar satellite, and handheld
dry spell parameters on the yield of millet and sorghum in
sensors like Green seekers, N-tester, Spadometer, Crop Circle
Nigeria and they correlated 21 dry spell parameters with the
and Field Spec can be used to detect these signatures. Since
yield. Poonam et al. (2017) developed three models using
forecasting is done before the harvest of the crop, the weather
weather parameters (artificial variables generated from weekly
data that we deal with are of two types- known data recorded
weather values) as input data to forecast the yield of wheat in
till the day of forecasting and the unknown data, between the
Hisar, Harayana. Annu et al. (2018) forecasted rice yield by
forecasting day and the harvest. Different scientists have used
discriminant function analysis of yield and related it to its
various methods, mainly- Historical data, mean of historical
biometrical characters in U.P., India. Kour et al. (2018)
data, weather generator models, climate forecast models and
forecasted rice yield in Gujarat using the time series model.
satellite derived climate variables.
Rice yield data and historical weather data were used as inputs
Yield forecasting using statistical models- for the model. Dry matter production, Agro-meterological
Indices of Rice as influenced by methods of establishment
and transplanting dates (Chandrashekar et al. 2010). Patil et
al. (2012) developed three different statistical models to predict
the yield of wheat using remote sensing and vegetative
parameter in Dharwad. Yadav et al. (2018) made a pre harvest
50

forecast of pigeonpea by regression analysis of weather

Latitude(degree)

variables in U.P. Mahapatra and Dash (2019) forecasted the

production of green gram in Odisha by time series model
using the best fit ARIMA (2,1,0) model. Sarvesh et al. (2019)
0

forecasted rapeseed and mustard yield for different years in

the Sultanpur district of U.P. using a discriminate functional
analysis of weather data. Girma et al. (2006) used the NDVI,
-50

leaf color, and chlorophyll content measured by the SPAD

meter in the multiple linear regression to forecast wheat yield
under nutrient application treatments at the Feekes 7 stage
-100 -200 0 100 200 (second node appearance). Gero et al. (2017) used the
Latitude(degree) proximally sensed reflectance data of 34 cultivars to develop
Figure 1: Country wise crop yield forecasting
vegetation indices and to calibrate PLSR models. They
concluded that PLSR and REIP gave superior predictions of
Citation-Baso and Liu(2018) grain yield of spring barley. Raja et al. (2014) used the time
Global(N=273) Africa(N=33) Americas(N=82)
series rainfall data of 25 years to derive the 1- and 3-month
Standardized Precipitation Index of different wet season
months and related the meteorological drought and its impact
on rice productivity in Odisha. Patel et al. (2006) used the
remotely sensed estimates of the fraction of absorbed
photosynthetically active radiation (fAPAR) and daily
temperature as input to a simple model based on light-use
Asia(N=84) Europe(N=66) Oceania(N=14) efficiency to estimate wheat yields at the pixel level in Harayana.
Ayyoob and Krishnadas (2013) developed the linear
correlation coefficient and multiple linear regression models
among yield with various weather factors of 13 years observed
during the stage of 50 per cent flowering of groundnut crop.
Sarika et al. (2011) used time series model to forecast the
pigeonpea yield by using the production data of 38 years.
Agrometeorological Remote sencing Verma et al. (2015) recommend using of linear mixed models
Process based Survey for pre-harvest yield forecasting of the mustard crop in
Figure 2: Region wise distribution of various crop yield forecasting Haryana. Pritam and Deepak (2018) correlated the
methods. transplanting data and biomass derived from remote sensing
data for its yield prediction in Shivamogga. Gupta et al. (2009)
These are mathematical equations (empirical models), by using
made a forecast and compared the forecasting methods using
independent variables like temperature, plant morphology,
parametric models like polynomial, logarithmic, inverse, and
remote sensor data etc forecasting of the dependent variable
exponential, with those of Box-Jenkins techniques like ARMA,

150
 SEASONAL CROP YIELD FORECASTING-METHODS, ACCURACIES AND LIMITATIONS

A agromet ,early 1 B process-based,early C remote sensing,early

3 8

6
2
4
1
2

0 0 0
50
D agromet ,mid E process-based,mid F remote sencing,mid
2
40
10
30

1 20
Number of papers

5
10

0 0 0

G agromet ,late H process-based,late 20 I remote sencing ,late

15 1
15
10
10
5
5

0 0 0
0.7-0.8
0.1-0.2

0.4-0.5
0.8-0.9

0.7-0.8
0.2-0.3

0.4-0.5

0.9-1.0
0-0.1

0.9-1.0

0.4-0.5
0.2-0.3
0-0.1
0.1-0.2
0.3-0.4

0.3-0.4

0.3-0.4
0.6-0.7

0.8-0.9
0.5-0.6

0.5-0.6
0.6-0.7

0.8-0.9

0.5-0.6

0.9-1.0
0.7-0.8
0-0.1

0.6-0.7
0.2-0.3
0.1-0.2
Range of reported r-squared values Citation-Basso and Liu (2018)
Figure. 3: Accuracy or r-squared values of crop yield forecasting
ARIMA using 41 years data in West Bengal. . Sellam and the satellite imagery and ground-based active optical sensors
Poovammal (2016) used Regression Analysis to predict rice to predict the yields in Sugar Beet, Spring Wheat, Corn, and
crop yield in Tamil Nadu. Barmeier et al. (2017) and Sunflower. Toshichika et al. (2018) used statistical models to
Christenson et al. (2016) forecasted barley yield at anthesis seasonal temperature and precipitation hindcast data, which
and soybean at yield early-to-mid reproductive stages using a were derived from a multi model ensemble (MME) in crops
PLS model with hyper-spectra reflectance. Sandeep et al. like maize, rice, wheat and sorghum. The analysis was
(2018) compared different efficiencies of different models in performed for five individual atmosphere-ocean coupled
predicting the yields of sugarcane using LANDSAT data. Prity general circulation model (GCM) and two MME datasets
et al. (2016) forecasted the yields of pigeonpea using different generated from average methods and the mosaic method.
linear and non-linear statistical models. Amrender and Sharma et al. (2018) forecasted Soybean and wheat crop yield
Lalmohan (2005) developed multiple linear regression models based on the statistical model in Malwa agroclimatic zone
to forecast the yield of Indian mustard using weather using weather variables and historical crop yield. Anup et al.
parameters. Sandeep et al. (2015) forecasted rice yield and (2006) predicted the corn and soybean crop yield for Iowa
jute over Bihar using weather parameters and technological using remote sensing and surface parameters by piecewise
trends. Dubey et al. (2018) developed empirical models linear regression method with breakpoint and a non-linear
between VCI and historical yield of sugarcane over 52 major Quasi-Newton multi-variate optimization method. Ajit Sharma
sugarcane-growing districts in five states of India by stepwise et al. (2016) used different time series modeling techniques
regression technique to forecast its yield. Mkhabela et al. like a straight line, second degree parabola, exponential,
(2011) reported that MODIS-NDVI could be used effectively modified exponential, Gompertz and logistic using the
to predict crop yields across the Canadian Prairies one to two secondary data from 1980-2010 to forecast the production of
months before harvest. Farai et al. (2014) predicted the maize apple in H.P, India. Vijaya et al. (2005) predicted the yield of
yield throughout Zimbabwe by regressing the number of dry castor and found that the canopy air-temperature differentials
dekads derived from VCI against official ground-based maize using infrared thermometer and yield were inversely related.
yield estimates to generate simple linear regression models. Kogan et al. (2013) forecasted the wheat yield in Ukraine by
Bu et al. (2017) developed linear regressions and compared using NDVI values from the MODIS, at 250 m spatial resolution.

151
M. HANUMANTHAPPA et al.,

Prity Kumara et al. (2014) developed different Autoregressive management parameters like planting date, derived from
Integrated Moving Average (ARIMA) models by using time satellite data in crop simulation model WOFOST.
series data of sixty two years (1950-2012) to forecast the rice (Hanumanthappa et al., 2010) recorded the pattern of annual
yield in India and concluded that ARIMA (1, 1, 1) is the best and seasonal rainfall variability in coastal district of Karnataka.
fitted model. Rohit et al. (2020) used Agriculture Production Systems
Crop simulation models (CSM)- Simulator (APSIM) model to know the impact of climate change
(change in temperature and rainfall patterns) on the productivity
These are computer software packages that are readily of maize in the state Madhya Pradesh by using 74 soil profiles
available to plot the data and fit the model. They are alternative from thirty districts. Jia et al. (2011) observed that the WOFOST
and less time consuming means of determining the optimum model could simulate wheat yield with a difference of less
crop yield. The Decision Support System for Agrotechnology than five percent while validating the WOFOST model in North
Transfer (DSSAT) is a software application program comprising China. Ghosh et al. (2014) developed a rice yield prediction
crop simulation models for over 42 crops (Version 4.7) and system for Bhubaneswar, India, by combining the extended
tools to facilitate effective use of the models. It was developed range forecast and CERES-rice model. Kulapramote et al.
by the International Benchmark Sites Network for Agro- (2018) used the Aqua Crop model and moderate-resolution
technological Transfer (IBSNAT) in the 1980s, with the first satellite images to simulate the rice yield for small-scale farmers.
official release in 1989. The development has continued in Gowtham et al. (2020) studied the impact of global warming
affiliation with the International Consortium for Agricultural (temperature increase of 1.5ºC) on the productivity of C3 and
Systems Applications (ICASA). DSSAT is like a shell storing C4 crops like rice and maize in the year 2035 and 2053 in
different CSM. The main advantage of using CSM is that it Tamil Nadu using DSSAT. Dua et al. (2020) studied the impact
mimics daily plant growth. Mojarad et al. (2018) in Iran of climate change on the productivity of three potato varieties
forecasted the yield of safflower under different saline irrigation in Madhya Pradesh using the WOFOST crop growth
strategies using the Aqua Crop model, version 4.0. Pal et simulation model in 38 locations.
al. (2013) forecasted the wheat yield in Palampur, H.P. using
Accuracies
the CERES Wheat model for which stochastic weather
generator was used to get the unknown weather data. Nain et The accuracy of the methods was represented as the r-squared
al. (2004) forecasted the yield of wheat using the CERES wheat values between the forecasted yield and the observed grain
model and two different technology trends in central IGP of yields. Basso and Liu (2018) grouped the reported r-squared
India. Sarvesh et al. (2019) forecasted the yield of several value based on the forecasting methods (statistical, process
chickpea cultivars under different sowing dates using DSSAT based and remote sensing) and forecasting time (early, mid
software version 4.6. Walikar et al. (2018) studied the impact and late crop stage) (Fig. 3). It is observed that when the
of climate change by forecasting the yield of soybean variety forecasting time progressed, the accuracy also increased (fig.
JS20-29 at different locations of Madhya Pradesh, India, using 3 A, D, G and fig. 3 C, F, I). Forecasting at early stages in all the
the CROPGRO model. Vimal et al. (2019) forecasted the yield techniques has a predominant r2 value of 0.5-0.6. Similarly,
of different chickpea varieties for finding out the suitable date forecasting during later stages has a predominant r2 value of
of sowing using the DSSAT model in U.P. Kamal et al. (2018) 0.7-0.8 (fig. 3 A, C and fig. 3 G, I). The process based models
used DSSAT-CERES-Rice model to forecast the yield under (CSM) are evaluated using different methods like frequency
different nitrogen levels in Meghalaya. Debjyoti and Lalu distribution, probability distribution and measure of central
(2018) forecast rice yield under different nitrogen and irrigation tendency rather than r2 value. The forecasting of the yield at
management levels in West Bengal using ORYZA2000. later stages, i.e., one month before harvest, gives a satisfactory
Mumtaz et al. (2018) predicted the cotton yield with a new forecasting result.
hybrid copula driven approach that combined the Markov Limitations of models in crop yield forecasting
Chain Monte Carlo-based simulation model with genetic Most of the model needs to be calibrated to represent the
programming algorithm. Machakaire et al. (2016) forecasted genetics of the crops and such information is often not
the yield and tuber size of potato eight weeks before the final available. Lack of/improper crop model calibration causes
harvest by LINTUL-Potato-DSS model which used the linear inaccurate yield forecasts (Kolotii et al., 2015). Long-term good
relationship between radiation intercepted by the crop and quality datasets of yield, agro meteorological conditions, crop
radiation-use efficiency, long-term and actual weather and crop genetics and sensor data are required to develop efficient yield-
data. Julien et al. (2014) forecasted the yield of sugarcane by forecasting models which are difficult in some countries. Getting
an empirical relationship method, the Kumar-Monteith good quality remotely-sensed data and the post data-
efficiency model, and a forced-coupling method of a sugarcane acquisition process is a significant challenge. Yield-forecasting
crop model (MOSICAS) and the satellite-derived fraction of statistical models are specific to crops, users and regions and
absorbed photosynthetically active radiation. Abdul Haris et cannot be worked outside the range of parameterized
al. (2020) used the Info Crop model to forecast the crop yield conditions. Unforeseen events that occur between the
and duration of the potato crop in Bihar due to climate change. forecasting day and the harvest day reduce the precision of
Gang Li et al. (2011) used Hyper spectral remote sensing the forecasting.
combined with important biophysical parameters like CCD
and LAI successfully in castor growth assessment and yield RESULTS AND DISCUSSION
prediction on China’s coastal saline land using OSAVI model.
Rojalin et al. (2013) forecasted the wheat yield in Punjab state Depending on scientist, the models are calibrated and
of India by incorporating biophysical parameters like LAI and validated using recent 10 to 25 years field and experimental

152
 SEASONAL CROP YIELD FORECASTING-METHODS, ACCURACIES AND LIMITATIONS

data.Statistical models to forecast yield is relatively simple as it CERES-wheat,-maize and-rice models performances. In: Advances in
establishes a relation between the yield and input variables Agronomy. vol. 136. Academic Press, pp. 27–132.
like temperature, rainfall, historical data, etc. It is simple to use Bruno Basso and Lin Liu. 2018. Seasonal crop yield forecast: Methods,
and less parameter-intensive. Incorporating the remotely applications and accuracies. Adv. Agron. 154(5):201-255.
sensed information to the statistical models can improve the Bu, H., Sharma, L. K., Denton, A. and Franzen, D. W. 2017.
forecasting accuracy, particularly for large-scale yield forecasts Comparison of satellite imagery and ground-based active optical
(Manjunath et al., 2002). The number of parameters used in sensors as yield predictors in Sugar Beet, Spring Wheat, Corn, and
the process-based simulation models is larger. It results in the Sunflower. Agron. J. 109(1): 299-308.
interaction effects between weather, soil, crop, and Chandrashekhar, Hanumanthappa, M., Sridhara, S. and Jayaprakash.
management on the grain and biomass yield. There must be 2018. Dry matter production, Agro-meterological Indices of Rice as
proper long-term good quality datasets of yield, influenced by methods of establishment and transplanting dates. Int.
agrometeorological conditions, remotely sensed data, and J. Cur. Microbiol.App. Sci.7(9):
genetics of the crop to get higher accuracy. The skill in operating Christenson, B.S., Schapaugh, W.T., An, N., Price, K.P., Prasad, V.
software, generating remote sensing data, processing, And Fritz, A.K. 2016. Predicting soybean relative maturity and seed
interpretation and storage must be developed in the individuals. yield using canopy reflectance. CropSci. 56: 625–643.
There is a possibility of using AI and machine learning in Debjyoti Majumder and Lalu Das. 2018. Simulating the yield attributes
forecasting the crop yield to reduce human errors and get of Boro rice under nitrogen and irrigation management at Mohanpur,
higher accuracy. West Bengal using ORYZA2000. J. Agrometeorol. 20(1):72-74.
Dharmaraja, S., Vidyottama Jain, Priyanka Anjoy and Hukum Chandra.
2019. Empirical analysis for crop yield forecasting in India. Agric.
ACKNOWLEDGEMENT Res. 56: 9-17.
We acknowledge all the scientists mentioned in the review Dua, V.K., Radhika Patahnia, Tanvi Kapoor, Jagdev Sharma and
paper for their valuable contribution to the field of agriculture. AnchalRana. 2020. Climate change and potato productivity in Madhya
Pradesh-Impact and adaptation. J.Agrometeorol. 20(2): 97-104.
REFERENCES Dubey, S. K., Gavli, A. S., Yadav, S. K., Seema Sehgal, and Andray S.
S. 2018. Remote sensing-based yield forecasting for Sugarcane
Abdul, H., Chhabra, V., Bhatt, B.P. and Sikka, A. K. 2020. Yield and (Saccharum officinarumL.) crop in India. J. Indian Soc. Remote Sens.
duration of potato crop in Bihar under projected climate scenarios.J. 15(2): 57-63.
Agrometerol. 17(1): 67-73.
Erdle, K., Mistele, B., Schmidhalter, U.(2011. Comparison of active
Ajit Sharma, Chaudhary, V. K. and Shilpa. 2016. Time series models and passive spectral sensors in discriminating biomass parameters
for apple area and production in Himachal Pradesh. The Ecoscan. 10 and nitrogen status in wheat cultivars. Field Crop Res. 124: 74–84.
(1&2): 105-110.
Farai Kuri, Amon Murwira, Karin S. Murwira and Mhosisi Masocha.
Amrender Kumar and Lalmohan Bhar. 2005. Forecasting model for 2014. Predicting maize yield in Zimbabwe using dry dekads derived
yield of Indian mustard (Brassica juncea) using weather parameter. from remotely sensed Vegetation Condition Index. Int. J. App. Earth
Indian J. Agril. Sci.75(10): 688-90. Obs. Geoinfo, 33:39–46.
Annu, Sisodia, B.V.S. and Sunil Kumar. 2018. Pre-harvest forecast Gang Li., Huangshi Zhang., Xianghua Wu., Chuanyan Shi., Xianjin
model for rice yield based on biometrical characters: An application Huang and Pei Qin. 2011. Canopy reflectance in two castor bean
of discriminant function analysis. Int. J. Chem. Studies. 6(4): 2205- varieties(Ricinus communis L.) for growth assessment and
2208. yield prediction on coastal saline land of Yancheng District, China.
Anup, K., Prasad, Lim Chai, Ramesh, P. S. and Menas Kafatos. 2006. Indus. Crops Prod., 33(2011) PP.395–402.
Crop yield estimation model for Iowa using remote sensingand surface Gero, B., Katharina H., and Urs, S. 2017. Mid-season prediction of
parameters. Int. J. App. Earth Obs. Geoinfo. 8:26–33. grain yield and protein content of spring barley cultivars using high-
Asseng, S., Zhu, Y., Basso, B., Wilson, T., Cammarano, D., and Van throughput spectral sensing, European J. Agr. 90:108–116.
Neal, K. 2014. Simulation modeling: applications in cropping systems Ghosh, K., Ankita, S., Mohanty, U. C., Nachiketa A., Pal, R. K.,
A2- Alfen. In: Encyclopedia of Agriculture and Food Systems. Academic Singh, K. K. and Pasupalak, S. 2014. Development of a rice yield
Press, Oxford, pp. 102–112. prediction system over Bhubaneswar, India:combination of extended
Ayyoob, K.C. and Krishnadas, M. 2013. Production forecast of range forecast and CERES-rice model. Meteorol. Appl.,
groundnut (Arachis hypogaea L.) using crop yield-weather model. Girma, K., Martin, K.L., Anderson, R.H., Arnall, D.B., Brixey, K.D.,
Agric. Upd., 8(3): 436-439. Casillas, M.A.,Chung, B., Dobey, B.C., Kamenidou, S.K., Kariuki,
Bannari, A., Morin, D., Bonn, F., and Huete, A.R., 1995. A review S.K., Katsalirou, E.E.,Morris, J.C., Moss, J.Q., Rohla, C.T., Sudbury,
of vegetation indices. Remote Sens. Rev. 13: 95–120. B.J., Tubana, B.S., and Raun, W.R. 2006. Mid-season prediction of
Barmeier, G., Hofer, K., and Schmidhalter, U. 2017. Mid-season wheat-grain yield potential using plant, soil, and sensor measurements.
prediction of grain yield andprotein content of spring barley cultivars J. Pl. Nutr. 29: 873–897.
using high-throughput spectral sensing. European J. Agron. 90: 108– Gowtham, R., Geethalakshmi, V., Bhuvaneshwari, K., Senthil, A.,
116. Dhasarathan, M., Aromar Revi and Amir Bazaz. 2020. Impact of
Basso, B., Cammarano, D. and Carfagna, E. 2013. Review of crop global warming (1.5ºC) on the productivity of selected C3 and C4
yield forecasting methods and early warning systems. In: Proceedings crops across Tamil Nadu. J. Agrometeorol. 22(1): 7-17.
of the first meeting of the scientific advisory committee of the global Gupta, D., Sahu, P. K. and Banerjee, R. 2009. Forecasting Jute
strategy to improve agricultural and rural statistics, FAO Headquarters, production in major contributing countries in the world. J.Natural
Rome, Italy. Fibers. 6:127–137.
Basso, B., Liu, L., Ritchie, J.T. 2016. A comprehensive review of the Gupta Smita, Ajit Singh, Ashok Kumar, Shahi, U.P., Nishant Sinha

153
M. HANUMANTHAPPA et al.,

and Sumana Roy. 2018. Yield forecasting of wheat and mustard for AquaCrop model in semi-arid regions. Australian J. Crop
western Uttar Pradesh using statistical model. J. Sci.12(08):1241-1249.
Agrometeorol.20(1):66-68. Mumtaz Ali, Ravinesh C. Deo, Nathan J. Downs and Tek Maraseni.
Hanumanthappa, M., T. H. Ranjith, R. Nagaraj, K.V. Sudhirkamath, 2018. Cotton yield prediction with Markov chain Monte Carlo-based
B. Dhanajaya and V.R. Vinod. 2016a. Impact of agromet Advisories simulation model integrated with genetic programing algorithm: A
issued based on medium range weather forecast on economics of new hybrid copula driven approach. Agril. For. Meteorol. 263:428–
different crops in Udupi district of Karnataka. Progr. Res.-An Inter. J. 448.
11(8): 4896-4898. Murata, Y. 1975. Estimation and simulation of Rice yield from climatic
Hanumanthappa, M., M. R. Ananda, P. SridharaHerle, L. Nagesha factors. Agric. Meteorol. 15: 117–131.
and K.V. SudhirKamath. 2010. Annual and seasonal rainfall variability Nain, A.S., Dadhwal, V. K. and Singh, T.P. 2004. Use of CERES-
in coastal district of Karnataka. J. Agrometeorology. 12(2):266-267. wheat model for wheat yield forecast in central Indo-Gangetic plains
Hanumanthappa, M., T. H. Ranjith, R. Naragaj and B. Dhananjaya. of India. J. Agric. Sci. 142: 59-70.
2016b. Impact of m-Kisan SMS in adoption of Agricultural Pal, R. K., Sehgal, V. K., Misra, A. K., Ghosh, K., Mohanty, U. C. and
Technologies by farmers of Udupi district of Karnataka. Adv. Life Sci. Rana, R.S. (2013). Application of seasonal temperature and rainfall
5(21): 9757-9759. forecast for wheat yield prediction for Palampur, Himachal Pradesh.
Jia, Y., Shen, S., Niu, C., Qiu, Y., Wang, H. and Liu, Y. 2011. Int. J. Agri. Food Sci. Tech. 4(5): 253-460.
Coupling crop growth andhydrologic models to predict crop yield Patel, N. R., Bhattacharjee B., Mohammeda. J., Tanupriy, A.B. and
with spatial analysis technologies. J.App. Remote Sens., 5. Saha, S. K. 2006. Remote sensing of regional yield assessment of
Julien Morel, Pierre Todoroff, Agnès Bégué, Aurore Bury, Jean- wheat in Haryana, India. .Int. J. Remote Sensing. 27(19):4071–4090.
François Martiné and Michel Petit. 2014. Toward a satellite-based Patil, S.S., Patil, V.C., Patil, B.N., and Patil, P.L. 2012. Simple yield
system of Sugarcane yield estimation and forecasting in small holder prediction models to estimate wheat production. Agro-Informatics
farming conditions: A case study on reunion Island. Remote and Precision Agriculture. pp. 162-166.
Sens. 6:6620-6635.
Patricia Oteng-Darko, Yeboah S., Addy S. N. T., Amponsah S. and
Kamal Kant, Pradip K. Bora and U.S. Saikia. 2018. Calibration of Owusu Danquah E. 2013. Crop modeling: A tool for agricultural
DSSAT CERES Rice model for rice cultivars under different N-levels in research – A review. J. Agril. Res.Develop. 2(1):001-006.
Meghalaya, India. J. Agrometeorol. 20(4):322-324. Poonam, Aneja, D.R., Khichar, M.L., Mamta, and Nitin Tanwar.
Kogan, F., Kussul, N., Adamenko, T., Skakun, S., Kravchenko, O., 2017. Statistical models for wheat yield forecasting using
Kryvobok, O., Shelestovb, O., Kolotii, A., Kussul, O., and Lavrenyuk, weatherparameters for western agroclimatic zone of Haryana.
A. 2013. Winter wheat yield forecasting in Ukraine based on Earth Bull.Env.Pharmacol. Life Sci. 6(4): 424-427.
observation, meteorological data and biophysical models. Int. Pritam. O. B., and Deepak, C. L. 2018. Estimation of rice yield and
J. Appl. Earth Obser. Geo inform. 23: 192–203. transplanting date by using satellite data in Karnataka state of India. J.
Kolotii, A., Kussul, N., Shelestov, A., Skakun, S., Yailymov, B., Basarab, Pharmacog. Phytochem. 7(6): 757-761.
R., Lavreniuk, M., OLIinyk, T. and Ostapenko, V. 2015. Comparison Prity Kumari, Mishra, G. C. and Srivastava, C P. 2016. Statistical
of biophysical and satellite predictors for wheat yield forecasting in models for forecasting pigeonpea yield in Varanasi region
Ukraine. In: Schreier, G., Skrovseth, P.E., Staudenrausch, H. (Eds.), J.Agrometeorol. 18(2): 306-310.
36th International Symposium on Remote Sensing of Environment.
47, pp.39–44. Prity Kumari, Mishra, G. C., Anil Kumar Pant, Garima Shukla and.
Kujur, S. N. 2014. Autoregressive integrated moving average (ARIMA)
Kour Satvinder, Shitap, M. S., Pradhan, U. K., Paul, R. K, Arya, P., approach for prediction of rice (Oryza sativa L.) yield in India. The
and Kumar, A. 2018. forecasting of rice yield based on weather Bioscan 9(3): 1063-1066.
parameters in kheda district of Gujarat, India. Int. J. Agricult. Stat. Sci.
Raja, R., Nayak, A. K., Panda, B. B., Lal, B., Rahul Tripathi,
14(2):611-615.
Mohammad Shahid, Anjani Kumar, Sangita Mohanty, Samal, P.,
Kulapramote Prathumchai , Masahiko Nagai, Nitin K., Tripathi and Priyanka Gautam and Rao, K.S. 2014. Monitoring of meteorological
Nophea Sasaki. (2018). Forecasting transplanted rice yield at the farm drought and its impact on rice (Oryza sativa L.) productivity in Odisha
scale using moderate-resolution satellite imagery and the aqua crop using standardized precipitation index. Arc. Agr. Soil Science. 1-14
model: a case study of a rice seed production community in Thailand.
Ranjan Rajeev, Nain, A. S. And Renu Panwar. 2012. Predicting yield
Int. J. Geo-Inf. 7(73):1-25.
of wheat with remote sensing and weather data. J. Agrometeorol.
Machakaire, A. T. B., Steyn J. M., Caldiz, D. O. and Haverkorta. J. 4(14):390-392.
2016. Forecasting Yield and tuber size of processing potatoes in
Rohit Patidar, Mohanty, M., Nishant K. S., Gupta S.C.,
South Africa using the Lintul-potato-DSS model. Potato Research.
Somasundaram, J., Chaudhary, R.S., Soliya, R., Hati, K.M., Prabhakar,
59:195–206.
M., Sammi Reddy, K., Patra, A.K. and Srinivas Rao, C.H. 2020,
Mahapatra, S.K. and Dash, A. 2019. Forecasting area and production Potential impact of future climate change onmaize (Zea mays L.)
of green gram in Odisha using ARIMA model. Int. J. Chem. Studies. under rainfed condition in central India. J.Agrometeorol. 22(1): 18-
7(3): 3899-3904. 23.
Manjunath, K.R., Potdar, M.B., Purohit, N.L. 2002. Large area Rojalin, T., Karshan, N. C., Joydeep, M., Shibendu, S. R., Patel, N.
operational wheat yield model development and validation based on K., Sushma, P. and Jai, S.P. 2013. Forecasting wheat yield in Punjab
spectral and meteorological data. Int. J. Remote Sens. 23: 3023– state of India by combining crop simulation model WOFOST and
3038. remotely sensed inputs. Remote Sensing Letters. 4(1):19–28.
Mkhabelaa, M.S., Bullock, A.P., Raj, B. S., Wang, C.S. and Yang, C.Y. Sandeep K. P., Giri R.K., Singh K.K. and Baxla A.K. 2015. Rice and
2011. Crop yield forecasting on the Canadian prairies using MODIS Jute yield forecast over Bihar region. Int. Res. J. Eng. Technol. 2(3):1636-
NDVI data. Agril. For.Meteorol.151(2011):385–393. 1647.
Mojarad, R. A. M. Z., Feizi, M. and Ghobadinia, M.2018. Prediction Sandeep, K.S., Rahul, D.G. and Om, P. D. 2018. Spatiotemporal
of safflower yield under different saline irrigation strategies using analysis of LANDSAT data for crop yield Prediction. J. Eng. Sci. Tech.

154
 SEASONAL CROP YIELD FORECASTING-METHODS, ACCURACIES AND LIMITATIONS

Review. 11(3): 9 – 17. Toshichika, I., Yonghee, S., Wonsik, K., Moosup, K. and Jaewon
Sarika, Iquebal, M .A. and Chattopadhyay, C.2011. Modelling and Choi. 2018. Global crop yield forecasting using seasonal climate
forecasting of pigeonpea (Cajanuscajan) production using information from a multimodel ensemble. Climate services. 11(2018):
autoregressive integrated moving average methodology. .Ind. J. Agril. 13-23.
Sci. 81(6): 520–523.
Verma, U., Piepho, H, P., Hartung, K., Ogutu J. O. and Goyal, A.
Sarvesh B., Mishra, A.N., Singh, A.K., Mishra, S.R., Sharma, S.K. and
Singh, D.P. 2019. Evaluation of crop simulation modeling in chickpea 2015. Linear Mixed Modeling for Mustard Yield Prediction in Haryana
crop using DSSAT model ver4.6. Int. J. Chem. Studies. 7(2): 655-658. State (India).J. Mathema. Statist. Sci. 5:96-105.
Sarvesh Kumar, Rai, V.N., Mourya, K.K., Annu and Ravi Prakash Vijaya, K. P., Ramakrishna, Y.S., Bhaskara Rao, D.V., Sridhar, G.,
Gupta. 2019. Forecasting of pre-harvest rapeseed and mustard yield Srinivasa Rao, G. and Rao, G.G.S.N. 2005. Use of remote sensing
using discriminant function analysis of meteorological parameters. for drought stress monitoring, yield prediction and varietal evaluation
Int. J. Chem. Studies. 7(3): 1897-1900.
in castor beans (Ricinus communis L.). Int. J. Remote Sens.
Sawa, B.A. and Ibrahim, A.A. 2011. Forecast models for the yield of
26(24):5525-5534.
millet and sorghum in the semi arid region of northern Nigeria using
dry spell parameters. Asian J. Agric. sci. 3(3): 187-191. Vimal Pandey, Singh, A.K., Mishra, S.R., Gulab Singh, Krishna Deo
Sellam, V. and Poovammal E. 2016. Prediction of crop yield using and Adita Mishra. 2019. Evaluation of crop simulation modeling in
regression analysis. Ind. J.Sci. Tech. 9(38):1-5. chickpea crop using DSSAT model under agroclimatic conditions of
Sharma, S.K., Bhagat D.V., Ranjeet, Pratiksha D., Khapedia, H.L., eastern U.P. The Pharma Innovation J. 8(4): 1139-1142.
Indra, S.M. and Ravindra, S.S. 2018. Soybean and wheat crop yield Walikar, L.D., Bhan, M., Giri, A.K., Dubey, A.K. and Agrawal, K.K.
forecasting based on statistical model in Malwa agroclimatic zone.
2018. Impact of projected climate on yield of soybean using
Int. J. Chem. Stud. 6(4): 1070-1073.
CROPGRO-soybean model in Madhya Pradesh. J.Agrometeorol.
Sreenivasan, P.S. and Banerjee, J.R. 1978. Behaviour of the Co-25 20(3): 211-215.
variety of irrigated rice under two environments. Agric. Meteorol. 19:
189–202. Yadav, R. R., Rudra Pratap Singh and Sisodia, B. V. S. 2018. Pre-
Thompson, L.M. 1969. Weather and technology in the production of harvest forecast of pigeon-pea yield using regression analysis of weather
corn in the US corn belt. Agron. J. 61(3):453-456. variables.Pl. Arch. 18(1): 913-916.

155
156