Search

Current study was conducted in collaboration with Department of Computer Sciences and Engineering, University of Engineering and technology, Lahore, Pakistan during 2020. As a result, the focus of this work was on the development of a pre-harvest crop yield forecasting model based on soil and environmental parameters. These parameters were recorded on a monthly basis at National Tea & High Value Crops Research Institute (NTHRI) for a period of ten years. The parameters recorded were minimum and maximum temperature, humidity, rainfall, soil pH level, pesticide use, and labor expertise. To construct the feature set for model training, exploratory feature analysis, outlier analysis, feature scaling, feature transformation and feature selection using the ReliefF algorithm were performed. Through 10-fold cross validation, six regression algorithms were used for training and model evaluation. An ensemble of neural networks were used to build the final model. The ensemble were built using a novel method that trains several base learners with architectural and training data diversity. These trained models were ranked using the ReliefF algorithm and sequentially added to the ensemble until the validation performance stops improving. On the basis of four performance metrics, the final model was compared to the four best performing models. The proposed model provided mean averave error (MAE), mean squared error (MSE) and root mean squared error (RMSE) of 0.0942, 0.0145, and 0.1204, respectively, and an R-squared of 0.9461. The performance parameters were the best among the candidate models and were sufficient to justify its use as a tea crop yield prediction model. [ABSTRACT FROM AUTHOR]

In countries like Pakistan, whose economy greatly depends on agriculture and predominantly crop production, the estimation of crop yield before harvesting is very important. Remote sensing allows early estimation of crop yield before harvesting. The objective of the study is to evaluate the possibility of MODIS-derived vegetation indices using GIS and RS to estimate pre-harvest wheat yield in the Potohar region, Pakistan. Two MODIS products MOD15A2H and MOD13A1 for the period 2009–2018 were used for the derivation of LAI and indices. Wheat yield data of each district for the study period were obtained from the agriculture statistics of Pakistan. Model was run using 16-days composite MODIS vegetation indices as independent variable and crop yield data as the dependent variable. To check the ability and accuracy of the model RMSE, MAE and MBE were calculated. Overall, the percentage average difference between the actual and predicted yield was within −1.986%. Average RMSE and MAE values ranged from 34.28 to 76.50 kg/ha and 108.09 to 129.99 kg/ha, respectively. The MBE value ranged from 7.20 to 62.80 kg/ha. The results concluded that accurate wheat yield predication can be made almost 2 months before harvesting using geospatial techniques along with the statistical modeling approach. [ABSTRACT FROM AUTHOR]

Remote sensing-based crop yield estimation methods rely on vegetation indices, which depend on the availability of the number of observations during the year, influencing the value of the derived crop yield. In the present study, a robust yield estimation method was improved for estimating the yield of corn, winter wheat, sunflower, and rapeseed in Hungary for the period 2000–2020 using 16 vegetation indices. Then, meteorological data were used to reduce the differences between the estimated and census yield data. In the case of corn, the best result was obtained using the Green Atmospherically Resistant Vegetation Index, where the correlation between estimated and census data was R2 = 0.888 before and R2 = 0.968 after the meteorological correction. In the case of winter wheat, the Difference Vegetation Index produced the best result with R2 = 0.815 and 0.894 before and after the meteorological correction. For sunflower, these correlation values were 0.730 and 0.880, and for rapeseed, 0.765 and 0.922, respectively. Using the meteorological correction, the average percentage differences between estimated and census data decreased from 7.7% to 3.9%, from 6.7% to 3.9%, from 7.2% to 4.2%, and from 7.8% to 5.1% in the case of corn, winter wheat, sunflower, and rapeseed, respectively.

As farming practices become increasingly automated, the quantity of high resolution on-farm production information grows exponentially and so does the need for high-throughput computing solutions to aid management. High resolution (5 m) wheat yield forecasting is presented here using two machine learning approaches: (a) Bootstrapped Regression Trees (BRR) where predictions are pixel-wise and (b) Convolutional Neural Networks (CNN) where predictions use neighbouring pixels. This study focused on three aims. First, to compare the two approaches in a yield forecasting task that included publicly available data and on-farm gathered yield data. Second, to study any benefit of adding more layers of information in the modelling process, e.g. proximal soil sensing surveys. Third, to evaluate the value of including information from contiguous neighbouring fields in order to forecast within-field wheat yield at harvest. Results showed that BRR modelling using publicly available Sentinel data with the addition of local electromagnetic induction surveys or gamma radiometric surveys produced the best forecasts as determined by the classical performance metrics. The results from the CNN models improved with the addition of publicly available data from neighbouring fields and produced a spatial distribution pattern that most closely resembled the actual yield data. Within-field yield forecasting using machine learning techniques and publicly available data shows good potential, and this work suggests that the choice of yield forecasting methodology may depend on the type and extent of spatial data that is available for use in forecasting. [ABSTRACT FROM AUTHOR]

Weather conditions regulate the growth and yield of crops, especially in rain-fed agricultural systems. This study evaluated the use and relative importance of readily available weather data to develop yield estimation models for maize and soybean in the US central Corn Belt. Total rainfall (Rain), average air temperature (Tavg), and the difference between maximum and minimum air temperature (Tdiff) at weekly, biweekly, and monthly timescales from May to August were used to estimate county-level maize and soybean grain yields for Iowa, Illinois, Indiana, and Minnesota. Step-wise multiple linear regression (MLR), general additive (GAM), and support vector machine (SVM) models were trained with Rain, Tavg, and with/without Tdiff. For the total study area and at individual state level, SVM outperformed other models at all temporal levels for both maize and soybean. For maize, Tavg and Tdiff during July and August, and Rain during June and July, were relatively more important whereas for soybean, Tavg in June and Tdiff and Rain during August were more important. The SVM model with weekly Rain and Tavg estimated the overall maize yield with a root mean square error (RMSE) of 591 kg ha−1 (4.9% nRMSE) and soybean yield with a RMSE of 205 kg ha−1 (5.5% nRMSE). Inclusion of Tdiff in the model considerably improved yield estimation for both crops; however, the magnitude of improvement varied with the model and temporal level of weather data. This study shows the relative importance of weather variables and reliable yield estimation of maize and soybean from readily available weather data to develop a decision support tool in the US central Corn Belt. [ABSTRACT FROM AUTHOR]

Accurate and timely information about production estimates of wheat is useful for policymakers and government planners. The traditional methods for yield forecasting are labor insensitive and time-consuming therefore remote sensing is an effective approach for precise yield forecasting. The study was planned to develop a comprehensive framework for yield forecasting and to assess interannual yield variability in semi-arid regions. For wheat area classification, the peak season Landsat-8 satellite images were acquired, and Top of Atmospheric (TOA) correction was performed. The ground-truthing points of 100 farms were collected from the study area for the training of algorithms. The eight machine learning algorithms were used tune and tested using 10-k fold cross-validation and the best model was used for land cover classification of wheat. For yield forecasting, the temporal normalized difference vegetation index (NDVI) and land surface temperature (LST) were derived for the wheatgrowing season from November to April. A Principal Component Analysis (PCA) was used to variable selection and then Least Absolute Shrinkage Selection Operator (LASSO) analysis was performed to develop coefficients of the yield forecasting model. The developed model was further used in yield forecasting of 10 years (2008-2018) in four semi-arid regions. The predicted yield was compared with Crop Reporting Service (CRS), Pakistan department. The results of all machine learning algorithms showed an accuracy of 88% to 96%, however, the Random forest algorithm showed higher accuracy, which was further used for classification. The wheat estimated area of 6.9% was less than reported by CRS. For interannual variability, the relationship of observed (CRS) and predicted yield of 10 years showed a close relation with R2 ranged from 0.69 to 0.75 in the semi-arid region of Punjab, Pakistan. It was concluded that machine learning algorithms can be used as novel tools for yield forecasting and assessment of interannual yield variability. [ABSTRACT FROM AUTHOR]

Subseasonal-to-seasonal (S2S) prediction of winter wheat yields is crucial for farmers and decision-makers to reduce yield losses and ensure food security. Recently, numerous researchers have utilized machine learning (ML) methods to predict crop yield, using observational climate variables and satellite data. Meanwhile, some studies also illustrated the potential of state-of-the-art dynamical atmospheric prediction in crop yield forecasting. However, the potential of coupling both methods has not been fully explored. Herein, we aimed to establish a skilled ML–dynamical hybrid model for crop yield forecasting (MHCF v1.0), which hybridizes ML and a global dynamical atmospheric prediction system, and applied it to northern China at the S2S time scale. In this study, we adopted three mainstream machining learning algorithms (XGBoost, RF, and SVR) and the multiple linear regression (MLR) model, and three major datasets, including satellite data from MOD13C1, observational climate data from CRU, and S2S atmospheric prediction data from IAP CAS, used to predict winter wheat yield from 2005 to 2014, at the grid level. We found that, among the four models examined in this work, XGBoost reached the highest skill with the S2S prediction as inputs, scoring R2 of 0.85 and RMSE of 0.78 t/ha 3–4 months, leading the winter wheat harvest. Moreover, the results demonstrated that crop yield forecasting with S2S dynamical predictions generally outperforms that with observational climate data. Our findings highlighted that the coupling of ML and S2S dynamical atmospheric prediction provided a useful tool for yield forecasting, which could guide agricultural practices, policy-making and agricultural insurance.

Accurate and timely information on yield forecasting is necessary for policymakers in decision-making. The case study was planned to develop a framework for the regional wheat yield forecasting model for southeastern Turkey. Therefore, after implementing Top of Atmospheric (TOA) correction for all images and collecting ground-truthing point of 313 fields from the Nurdagi and Islahiye counties. A total of eight machine learning algorithms were tuned and tested for the satellite image classification so that best model was used for the spatial distribution of wheat crop. The results of machine learning algorithms showed an accuracy greater than 90%. As the best model, the random forest was used for image classification. The classification results showed that area estimated by the classifier were 11% more than those reported by the Turkish statistical department. The observed and predicted yield of the tested model was closed to each other with root mean square error (RMSE) of 198 kg ha−1. The observed and predicted yield showed a close agreement with RMSE of 144 kg ha−1 at Nurdagi and 68 kg ha−1 at Islahiye for 5 years. It is concluded that remote sensing is useful tools for estimation of yield and developed can be used for other regions and crops. [ABSTRACT FROM AUTHOR]

In order to develop weather-based yield prediction models for rice and grass pea in coastal saline zone of West Bengal, the experiments were conducted with rice (cv. CR 1017) and grass pea (cv. Bio L 212) in the rainy and winter seasons, respectively of 2016-17 and 2017-18. Rice was sown in nursery bed on six different dates starting from June 15 to July 19 at weekly interval in both rainy seasons in two different land situations viz. medium upland and medium lowland. Likewise, grass pea was sown on six different dates just before harvesting of rice. It was observed that both early sown rice and grass pea resulted in higher grain yield and took more time to mature under medium lowland situation irrespective of sowing dates. Correlation study revealed that air temperature during sowing to transplanting phase exhibited significant positive correlation with grain of rice in medium upland (Tmax = 0.76**, Tmin = 0.69*) and medium lowland (Tmax = 0.93**, Tmin = 0.81**) situations. On the other hand, maximum temperature and total solar radiation during 100% emergence to 100% flowering stage were negatively associated with the grain yield of grass pea in both medium upland (Tmax = -0.69*, Accumulated solar radiation = -0.73**) and medium lowland (Tmax = -0.74**, Acc. solar radiation = -0.77**) situations. Grain yield of rice and grass pea could be predicted with 94.4% and 87.4% predictability. Pre-harvest forecasting of grain yield was possible with 77.3% for rice and 83.8% for grass pea. [ABSTRACT FROM AUTHOR]

Advance estimates of significant cereal and commercial crops are given by the Directorate of Economics and Statistics and the central Ministry of Agriculture, Cooperation & Farmers' Welfare. However, the final estimates are released a few months after the actual harvest of the crops. In this study, ARIMA and State-Space models have been developed for sugarcane yield forecasting in Ambala and Karnal districts of Haryana. The above-mentioned models have been developed using yield data of sugarcane crop for the time period 1966-67 to 2009-10 of Ambala and Karnal districts. The validity of fitted models has been tested over the years 2010-11 to 2016-17. The forecasting performance of the developed models has been studied using percent deviations of sugarcane yield forecasts in relation to the actual yield, and root means squared errors. It has been observed that state -space models outperform the popular ARIMA models for forecasting of sugarcane yield in Northern Agro -climatic Zone of Haryana. [ABSTRACT FROM AUTHOR]

Due to the increasing global demand of food grain, early and reliable information on crop production is important in decision making in agricultural production. Remote sensing (RS)-based forecast models developed from vegetation indices have the potential to give quantitative and timely information on crops for larger regions or even at farm scale. Different vegetation indices are being used for this purpose, however, their efficiency in estimating crop yield certainly needs to be tested. In this study, wheat yield was derived by linear regressing reported yield values against a time series of six different peak-seasons (2013–2018) using the Landsat 8-derived Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI). NDVI- and SAVI-based forecasting models were validated based on 2018–2019 datasets and compared to evaluate the most appropriate index that performs better in forecasting wheat production in the Tisza river basin. Nash-Sutcliffe efficiency index was positive with E1 = 0.716 for the model from NDVI and for SAVI E1 = 0.909, which means that the forecasting method developed and performed good forecast efficiency. The best time for wheat yield prediction with Landsat 8-SAVI and NDVI was found to be the beginning of full biomass period from the 138th to 167th day of the year (18 May to 16 June; BBCH scale: 41–71) with high regression coefficients between the vegetation indices and the wheat yield. The RMSE of the NDVI-based prediction model was 0.357 t/ha (NRMSE: 7.33%). The RMSE of the SAVI-based prediction model was 0.191 t/ha (NRMSE 3.86%). The validation of the results revealed that the SAVI-based model provided more accurate forecasts compared to NDVI. Overall, probable yield amount is possible to predict far before harvest (six weeks earlier) based on Landsat 8 NDVI and SAVI and generating simple thresholds for yield forecasting, and a potential loss of wheat yield can be mapped.

• Evaluate the potential using Landsat 8 vegetation index for jujube yield estimation. • Identify the phenology time for making a reliable jujube yield prediction. • Integrate phenology length to improve remote sensing-based yield forecasting model. • The proposed method showed better performance than the leave-one-year-out method. It is challenging to generate a time series of vegetation indices from moderate spatial resolution Landsat Thematic Mapper images (Landsat 8) for crop yield forecasting. In addition, crop yields are correlated with phenology information, especially the fruit filling days. The objectives of this study were to identify the phenology time for making a reliable jujube yield prediction, more importantly, explore an approach that used the length of phenology growth period to improve remotely sensed estimates of inter-annual variability for yields. The best time for making jujube yield prediction was found to be during the fruit filling period, showing higher correlation coefficient (r) between vegetation indices and yields. The average NDVI for 14th and 15th half-months represented a better performance for yield prediction, with a highest r value of 0.87 for NDVI, 0.82 for SAVI, 0.73 for NDWI and 0.73 for EVI, respectively. The potential of using Landsat-NDVI for jujube yield estimation, combined with the phenological length, was preliminarily proved based on 200 observations of individual jujube orchards, showing a validated R2 of 0.85, 0.80 and 0.67, RMSE of 0.61, 0.78 and 0.85 t ha−1 for 2013, 2014 and 2016, respectively. Furthermore, the phenological adjusted model was further evaluated by inter-annual official statistic data, with R2 and RMSE values ranging from 0.38 to 0.53, and 0.31 to 0.47 t ha−1, respectively. The proposed method showed better performance between years when the fruit filling days differed greatly than the leave-one-year-out method, which was verified to well fit to jujube yield monitoring and mapping two months before harvest. [ABSTRACT FROM AUTHOR]

Highlights • Novel use of neural networks and multitask learning for yield curve forecasting. • Multilayer perceptron using the most relevant features achieved the best results. • The most relevant features depend on target yield and forecasting horizon. • Synthetic data from linear regression model tends to improve forecasting accuracy. • Encouraging results for the development of robust forecasting systems for bond market. Abstract The yield curve is the centrepiece in bond markets, a massive asset class with an overall size of USD 100 trillion that remains relatively under-investigated using machine learning. This paper is the first comprehensive study using artificial neural networks in the context of yield curve forecasting. Specifically, two models were used for forecasting the European yield curve: multivariate linear regression and multilayer perceptron (MLP), at five forecasting horizons, from next day to 20 days ahead. Five variants of the MLP were analysed with different sets of features: target to predict (univariate); the most relevant features; all generated features; and the former two incorporating synthetic data generated by the linear regression model. Additionally, two different techniques of multitask learning were employed: simultaneous modelling and transformation into multiple single task learning. The results show that considering all forecasting horizons, the MLP using the most relevant features achieved the best results and the addition of synthetic data tends to improve accuracy. Furthermore, different targets and forecasting horizons resulted in different relevant features, reinforcing the importance of custom-built models. In the two multitask learning methodologies no clear differentiation could be demonstrated, and several explaining factors are identified. Overall, the outcome is very encouraging for the development of better forecasting systems for fixed income markets. [ABSTRACT FROM AUTHOR]

Abstract The WOFOST cropping systems model has been applied operationally over the last 25 years as part of the MARS crop yield forecasting system. In this paper we provide an updated description of the model and reflect on the lessons learned over the last 25 years. The latter includes issues like system performance, model sensitivity, spatial model setup, parameterization and calibration approaches as well as software implementation and version management. Particularly for spatial model calibrations we provide experience and guidelines on how to execute calibrations and how to evaluate WOFOST model simulation results, particularly under conditions of limited field data availability. As an open source model WOFOST has been a success with at least 10 different implementations of the same concept. An overview is provided for those implementations which are managed by MARS or Wageningen groups. However, the proliferation of WOFOST implementations has also led to questions on the reproducibility of results from different implementations as is demonstrated with an example from MARS. In order to certify that the different WOFOST implementations and versions available can reproduce basic sets of inputs and outputs we make available a large set of test cases as appendix to this publication. Finally, new methodological extensions have been added to WOFOST in simulating the impact of nutrients limitations, extreme events and climate variability. Also, a difference is made in the operational and scientific versions of WOFOST with different licensing models and possible revenue generation. Capitalizing both on academic development as well as model testing in real-world situations will help to enable new applications of the WOFOST model in precision agriculture and smart farming. Highlights • An updated description of the WOFOST model is provided • Guidelines for (spatial) calibration of WOFOST are provided • Current implementations of the model are described and issues with model proliferation are raised • New development and model extensions are described • A set of reference results is published that can be used to certify any WOFOST implementation. [ABSTRACT FROM AUTHOR]

Badland reclamation and low productive farmlands always have been one of the most detrimental effects on the national economy, typically in agricultural sector of Uzbekistan. Nonetheless, such kind of lands has been used extensively for major crops like cotton and winter wheat. However, it is difficult to assessing real productivity of them. Advanced technologies as GIS and RS are vital tool for geospatially analysing and making decisions on this type of fields. This research was carried out for real-time crop monitoring and yield forecasting in case of low productive (3.5 ha) and high productive (8.3 ha) cotton areas of Jarkurgan district (Surkhandarya region, Uzbekistan) based on geospatial analyses of multi-temporal satellite images, condition of groundwater, soil salinity, and ground truth data. For monitoring vegetation phenology of cotton and forecasting its harvest, False Colour, NDVI (Normalized Difference Vegetation Index) and SI (Salinity Index) analyses of areas were carried out by using 6 temporal windows of multi-temporal Sentinel 2 from April through August 2019. Besides, groundwater condition data which was obtained from observation wells these located in massives consists of both cotton fields was analysed by IDW (Inverse Distance Weighting) interpolation algorithm method to determine groundwater’s effect to vegetation development and yield.

Sorghum is an important dual-purpose crop of India grown for food and fodder. Prevailing weather conditions during the crop growth period determine the yield of sorghum. Hence, the crop yield forecasting models based on weather parameters will be an appropriate option for policymakers and researchers to develop sustainable cropping strategies. In the present study, six multivariate weather-based models viz., least absolute shrinkage and selection operator (LASSO), elastic net (ENET), principal component analysis (PCA) in combination with stepwise multiple linear regression (SMLR), artificial neural network (ANN) alone and in combination with PCA and ridge regression model are examined by fixing 90% of the data for calibration and remaining dataset for validation to forecast rabi sorghum yield for different districts of Karnataka. The R2 and root mean square error (RMSE) during calibration ranged between 0.42 to 0.98 and 30.48 to 304.17 kg ha−1, respectively, without actual evapotranspiration (AET) whereas, these evaluation parameters varied from 0.38 to 0.99 and 19.84 to 308.79 kg ha−1, respectively with AET inclusion. During validation, the RMSE and nRMSE (normalized root mean square error) varied between 88.99 to 1265.03 kg ha−1 and 4.49 to 96.84%, respectively without AET and including AET as one of the weather variable RMSE and nRMSE were 63.48 to 1172.01 kg ha−1 and 4.16 to 92.56%, respectively. The performance of six multivariate models revealed that LASSO was the best model followed by ENET compared to PCA_SMLR, ANN, PCA_ANN and ridge regression models because of reduced overfitting through penalisation of regression coefficient. Thus, it can be concluded that LASSO and ENET weather-based models can be effectively utilized for the district level forecast of sorghum yield.

Tea is a cash crop that improves the quality of life for people in the Tanuyen District of Laichau Province, Vietnam. Tea yield, however, has stagnated in recent years, due to changes in temperature, precipitation, the age of the tea bushes, and diseases. Developing an approach for monitoring tea bushes by remote sensing and Geographic Information Systems (GIS) might be a way to alleviate this problem. Using multi-temporal remote sensing data, the paper details an investigation of the changes in tea health and yield forecasting through the normalized difference vegetation index (NDVI). In this study, we used NDVI as a support tool to demonstrate the temporal and spatial changes in NDVI through the extract tea NDVI value and calculate the mean NDVI value. The results of the study showed that the minimum NDVI value was 0.42 during January 2013 and February 2015 and 2016. The maximum NDVI value was in August 2015 and June 2017. We indicate that the linear relationship between NDVI value and mean temperature was strong with R 2 = 0.79 Our results confirm that the combination of meteorological data and NDVI data can achieve a high performance of yield prediction. Three models to predict tea yield were conducted: support vector machine (SVM), random forest (RF), and the traditional linear regression model (TLRM). For period 2009 to 2018, the prediction tea yield by the RF model was the best with a R 2 = 0.73 , by SVM it was 0.66, and 0.57 with the TLRM. Three evaluation indicators were used to consider accuracy: the coefficient of determination ( R 2 ), root-mean-square error (RMSE), and percentage error of tea yield (PETY). The highest accuracy for the three models was in 2015 with a R 2 ≥ 0.87, RMSE < 50 kg/ha, and PETY less 3% error. In the other years, the prediction accuracy was higher in the SVM and RF models. Meanwhile, the RF algorithm was better than PETY (≤10%) and the root mean square error for this algorithm was significantly less (≤80 kg/ha). RMSE and PETY showed relatively good values in the TLRM model with a RMSE from 80 to 100 kg/ha and a PETY from 8 to 15%.

Early prediction of sugarcane crop yield at the commercial block level (unit area of a single crop of the same variety, ratoon or planting date) offers significant benefit to growers, consultants, millers, policy makers, crop insurance companies and researchers. This current study explored a remote sensing based approach for predicting sugarcane yield at the block level by further developing a regionally specific Landsat time series model and including individual crop sowing (or previous seasons’ harvest) date. For the Bundaberg growing region of Australia this extends over a five months period, from July to November. For this analysis, the sugarcane blocks were clustered into 10 groups based on their specific planting or ratoon commencement date within the specified five months period. These clustered or groups of blocks were named ‘bins’. Cloud free (-1) achieved for the respective bin over the five growing years, producing strong correlations (R2 = 0.92 to 0.99). The quadratic curves developed for the different bins were shifted according to the specific planting or ratoon date of an individual block allowing for the peak GNDVI value of the block to be calculated, regressed against the actual block yield (t·ha-1) and the prediction of yield to be made. To validate the accuracies of the 10 time series algorithms representing each of the 10 bins, 592 individual blocks were selected from the Bundaberg region during the 2019 harvest season. The crops were clustered into the appropriate bins with the respective algorithm applied. From a Sentinel image acquired on the 5 May 2019, the prediction accuracies were encouraging (R2 = 0.87 and RMSE = 11.33 (t·ha-1)) when compared to actual harvested yield, as reported by the mill. The results presented in this paper demonstrate significant progress in the accurate prediction of sugarcane yield at the individual sugarcane block level using a remote sensing, time-series based approach.

Early yield assessment at local, regional and national scales is a major requirement for various users such as agriculture planners, policy makers, crop insurance companies and researchers. This current study explored a remote sensing-based approach of predicting sugarcane yield, at district level, using Vegetation Condition Index (VCI), under the FASAL programme of the Ministry of Agriculture & Farmers’ Welfare. 13-years’ historical database (2003-2015) of NDVI was used to derive the VCI. NDVI products (MOD-13A2) of MODIS instrument on board Terra satellite at 16-day interval from first fortnight of June to second fortnight of October (peak growing period) were used to calculate the VCI. Stepwise regression technique was used to develop empirical models between VCI and historical yield of sugarcane over 52 major sugarcane-growing districts in five states of India. For all the districts, the empirical models were found to be statistically significant. A large number of statistical parameters were computed to evaluate the performance of VCI-based models in predicting district-level sugarcane yield. Though there was variation in model performance in different states, overall, the study showed the usefulness of VCI, which can be used as an input for operational sugarcane yield forecasting. [ABSTRACT FROM AUTHOR]

Copyright of Biotechnologie, Agronomie, Societe et Environnement is the property of Les Presses Agronomiques de Gembloux and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurately forecasting crop yield in advance of harvest could greatly benefit decision makers when making management decisions. However, few evaluations have been conducted to determine the impact of including weather forecasts, as opposed to using historical weather data (commonly used) in crop models. We tested a combination of short-term weather forecasts from the Weather Research and Forecasting Model (WRF) to predict in season weather variables, such as, maximum and minimum temperature, precipitation, and radiation at four different forecast lengths (14 days, 7 days, 3 days, and 0 days). This forecasted weather data along with the current and historic (previous 35 years) data were combined to drive Agricultural Production Systems sIMulator (APSIM) in-season corn [ Zea mays L ] and soybean [ Glycine max ] grain yield and phenology forecasts for 16 field trials in Iowa, USA. The overall goal was to determine how the inclusion of weather forecasting impacts in-season crop model predictions. We had two objectives 1) determine the impact of weather forecast length on WRF accuracy, and 2) quantify the impact of weather forecasts accuracy on APSIM prediction accuracy. We found that the most accurate weather forecast length varied greatly among the 16 treatments (2 years × 2 sites × 2 crops × 2 management practices), but that the 0 day and 3 day forecasts were, on average, the most accurate when compared to the other forecast lengths. Overall, the accuracy of the in-season crop yield forecast was inversely proportional to forecast length (p = 0.026), but there was variation among treatments. The accuracy of the in-season flowering and maturity forecasts were not significantly affected by inclusion of weather forecast length (p = 0.065). The 14 day forecast provided enough lead time to improve flowering prediction in 8 out of the 16 treatments. The fact that maximum temperature was the most accurate predicted variable by WRF was the reason for improvements in flowering predictions. Our results suggest that a weather forecast from WRF was not better than historical weather for yield prediction. [ABSTRACT FROM AUTHOR]

Crop yield forecasting plays a vital role in coping with the challenges of the impacts of climate change on agriculture. Improvements in the timeliness and accuracy of yield forecasting by incorporating near real-time remote sensing data and the use of sophisticated statistical methods can improve our capacity to respond effectively to these challenges. The objectives of this study were (i) to investigate the use of derived vegetation indices for the yield forecasting of spring wheat (Triticum aestivum L.) from the Moderate resolution Imaging Spectroradiometer (MODIS) at the ecodistrict scale across Western Canada with the Integrated Canadian Crop Yield Forecaster (ICCYF); and (ii) to compare the ICCYF-model based forecasts and their accuracy across two spatial scales-the ecodistrict and Census Agricultural Region (CAR), namely in CAR with previously reported ICCYF weak performance. Ecodistricts are areas with distinct climate, soil, landscape and ecological aspects, whereas CARs are census-based/statistically-delineated areas. Agroclimate variables combined respectively with MODIS-NDVI and MODIS-EVI indices were used as inputs for the in-season yield forecasting of spring wheat during the 2000–2010 period. Regression models were built based on a procedure of a leave-one-year-out. The results showed that both agroclimate + MODIS-NDVI and agroclimate + MODIS-EVI performed equally well predicting spring wheat yield at the ECD scale. The mean absolute error percentages (MAPE) of the models selected from both the two data sets ranged from 2% to 33% over the study period. The model efficiency index (MEI) varied between −1.1 and 0.99 and −1.8 and 0.99, respectively for the agroclimate + MODIS-NDVI and agroclimate + MODIS-EVI data sets. Moreover, significant improvement in forecasting skill (with decreasing MAPE of 40% and 5 times increasing MEI, on average) was obtained at the finer, ecodistrict spatial scale, compared to the coarser CAR scale. Forecast models need to consider the distribution of extreme values of predictor variables to improve the selection of remote sensing indices. Our findings indicate that statistical-based forecasting error could be significantly reduced by making use of MODIS-EVI and NDVI indices at different times in the crop growing season and within different sub-regions.

In East Africa, accurate grain yield predictions can help save lives and protect livelihoods. Regional grain yield forecasts can inform decisions regarding the availability and prices of key staples, food aid, and large humanitarian responses. Here, we use earth observation (EO) products to develop and evaluate subnational grain yield forecasts for 56 regions located in two severely food insecure countries: Kenya and Somalia. We identify, for a given region and time of year, which, if any, product is the best indicator for end-of-season maize yields. Our analysis seeks to inform a real-world situation in which analysts have access to multiple regularly updated EO data products, but predictive skill corresponding to each may vary across these regions and throughout the season. We find that the most accurate predictions can be made for high-producing areas, but that the relationship between production and forecast accuracy diminishes in areas with yields averaging greater than one metric ton per hectare. However, while forecast accuracy is highest in high production areas, in many of these regions, the forecast accuracy of models using EO products is not better than a set of baseline models that do not use EO products. Overall, we find that rainfall is the best indicator in low-producing regions and that other EO products work best in areas where yields are relatively consistent, but production is still limited by environmental factors.

Crop growth simulation models can simulate the processes of crop growth, development, yield formation, and its response to environment, which provides an effective method for crop yield forecast. However, how to select suitable weather data for the forecast is still an open question. In this study, we established a method for maize yield forecast based on maize growth simulation model of CERES-Maize and historical weather data from the year of 1956 to 2015. Two year's experimental data from 3 sites of Yangling (2014 and 2015), Heyang (2009 and 2011) and Changwu (2010 and 2011) in Shaanxi Province were used to test the reliable and accuracy of the method established. The weather data needed for model simulation were divided into 2 different groups including the known weather data and unknown weather data during the whole growth season of spring maize. The known weather data were obtained from local weather stations, while unknown data were supplemented with historical weather data of multiple years in the local experimental sites. Multiple complete climatic data series were then created and used to run the CERES-Maize model to forecast maize yield for a given year. As the advancing of maize growth season, the daily weather data were gradually merged into the observed weather data in a target year. Consequently, the daily maize yield was forecasted from sowing day to harvest. In addition, in order to reduce the times of model runs and reduce the uncertainties in yield forecasts, this study compared the daily meteorological data of historical and target years with normal K nearest neighbor (K-NN) and a modified K-NN algorithm to select several historical analogue years whose weather data were similar to the target year. The results showed that: 1) the model was suitable for the yield simulation since the absolute relative error was smaller than 15%; 2) the data distribution of predicted yields began to converge and the uncertainty decreased rapidly after the tasseling stage. For example, the predicted yield after 30, 60 and 90 days (the tasseling stage) of sowing was 3 531-14 461, 3 413-14 828 and 961-13 210 kg/hm2, respectively. But, the yield was 49 33-10 826, 8 484-10 565 kg/hm2, respectively after 100 and 130 days of sowing. The coefficient of variation had a sudden fall around the tasseling stage; 3) Yield forecast accuracy was generally lower than expectation for the method based on all historical data and climatic analogue years selected with historical data. The model run cost 61 min for a yield prediction during a complete growth stage of spring maize, indicting a necessary change in the prediction method optimization; 4) Among the 3 methods, the modified K-NN method showed a higher prediction accuracy and shorter run time than the other methods. The coefficient of variation was 11.7%-23.8% for the modified K-NN method, 15.1%-29.1% for the historical data, and 14.7%-26.9% for the K-NN method, respectively. To complete the yield prediction of a growth stage of spring maize, the modified K-NN method only took 14 min, which was shorter than the normal K-NN method. Thus, the modified K-NN method in this study had a big potential for the yield prediction by the CERES-Maize model. The study provides an effective method for selecting precipitation factor used for the yield prediction by crop models. [ABSTRACT FROM AUTHOR]

In order to assess the response of wheat and barley to climate variability, the correlation between variations of yields with local and global climate variables was investigated in west and northwest Iran over 1982-2013. The global climate variables were the El Niño-Southern Oscillation (ENSO), Arctic Oscillation (AO), and North Atlantic Oscillation (NAO) signals. Further, minimum ( T ), maximum ( T ), and mean ( T ) temperature, diurnal temperature range (DTR), precipitation, and reference evapotranspiration (ET) was used as local weather factors. Pearson's correlation coefficient was applied to analyze the relationships between climatic variables and yields. Unlike T , T , ET, and T , the yields were significantly associated with the entire growing season (EGS) DTR in most sites. Therefore, considering weather extreme variables such as DTR sheds light on the crop-temperature interactions. It is also found that the April-May-June (AMJ), October-November-December (OND), and EGS rainfall variations markedly influence the yields. Unlike the AO and NAO indices, the Niño-4 and SOI (the ENSO-related signals) were significantly correlated with the OND and EGS precipitation and DTR. Thus, the ENSO anomalies highly impact rainfed yields through influencing the OND and EGS rainfall and DTR in the studied sites. As the correlation coefficient of the OND and July-August-September (JAS) Niño-4 with yields was significant ( p < 0.05) for almost all locations, the JAS and OND Niño-4 may be a good proxy for cereal yield forecasting. Further, an insignificant increment and a significant reduction in yields are expected in La Niña and El Niño years, respectively, relative to neutral years. [ABSTRACT FROM AUTHOR]

The impact of extreme events (such as prolonged droughts, heat waves, cold shocks and frost) is poorly represented by most of the existing yield forecasting systems. Two new model-based approaches that account for the impact of extreme weather events on crop production are presented as a way to improve yield forecasts, both based on the Crop Growth Monitoring System (CGMS) of the European Commission. A first approach includes simple relations – consistent with the degree of complexity of the most generic crop simulators – to explicitly model the impact of these events on leaf development and yield formation. A second approach is a hybrid system which adds selected agro-climatic indicators (accounting for drought and cold/heat stress) to the previous one. The new proposed methods, together with the CGMS-standard approach and a system exclusively based on selected agro-climatic indicators, were evaluated in a comparative fashion for their forecasting reliability. The four systems were assessed for the main micro- and macro-thermal cereal crops grown in highly productive European countries. The workflow included the statistical post-processing of model outputs aggregated at national level with historical series (1995–2013) of official yields, followed by a cross-validation for forecasting events triggered at flowering, maturity and at an intermediate stage. With the system based on agro-climatic indicators, satisfactory performances were limited to microthermal crops grown in Mediterranean environments (i.e. crop production systems mainly driven by rainfall distribution). Compared to CGMS-standard system, the newly proposed approaches increased the forecasting reliability in 94% of the combinations crop × country × forecasting moment. In particular, the explicit simulation of the impact of extreme events explained a large part of the inter-annual variability (up to +44% for spring barley in Poland), while the addition of agro-climatic indicators to the workflow mostly added accuracy to an already satisfactory forecasting system. [ABSTRACT FROM AUTHOR]

This paper presents an intercomparative study of 12 operationally produced large-scale datasets describing soil moisture, evapotranspiration (ET), and/or vegetation characteristics within agricultural regions of the contiguous United States (CONUS). These datasets have been developed using a variety of techniques, including, hydrologic modeling, satellite-based retrievals, data assimilation, and survey/in-field data collection. The objectives are to assess the relative utility of each dataset for monitoring crop yield variability, to quantitatively assess their capacity for predicting end-of-season corn and soybean yields, and to examine the evolution of the yield-index correlations during the growing season. This analysis is unique both with regards to the number and variety of examined yield predictor datasets and the detailed assessment of the water availability timing on the end-of-season crop production during the growing season. Correlation results indicate that over CONUS, at state-level soil moisture and ET indices can provide better information for forecasting corn and soybean yields than vegetation-based indices such as normalized difference vegetation index. The strength of correlation with corn and soybean yields strongly depends on the interannual variability in yield measured at a given location. In this case study, some of the remotely derived datasets examined provide skill comparable to that of in-situ field survey-based data—further demonstrating the utility of these remote sensing-based approaches for estimating crop yield. [ABSTRACT FROM PUBLISHER]

This study explored the suitability of the Normalized Difference Vegetation Index (NDVI) from the Moderate Resolution Imaging Spectrometer (MODIS) obtained for six sugar management zones, over nine years (2002–2010), to forecast sugarcane yield on an annual and zonal base. To take into account the characteristics of the sugarcane crop management (15-month cycle for a ratoon, accompanied with continuous harvest in Western Kenya), the temporal series of NDVI was normalized through an original weighting method that considered the growth period of the sugarcane crop (wNDVI), and correlated it with historical yield datasets. Results when using wNDVI were consistent with historical yield and significant at P-value = 0.001, while results when using traditional annual NDVI integrated over the calendar year were not significant. This correlation between yield and wNDVI is mainly drawn by the spatial dimension of the data set (R2 = 0.53, when all years are aggregated together), rather than by the temporal dimension of the data set (R2 = 0.1, when all zones are aggregated). A test on 2012 yield estimation with this model realized a RMSE less than 5 t·ha−1. Despite progress in the methodology through the weighted NDVI, and an extensive spatio-temporal analysis, this paper shows the difficulty in forecasting sugarcane yield on an annual base using current satellite low-resolution data. This is particularly true in the context of small scale farmers with fields measuring less than the size of MODIS 250 m pixel, and in the context of a 15-month crop cycle with no seasonal cropping calendar. Future satellite missions should permit monitoring of sugarcane yields using image resolutions that facilitate extraction of crop phenology from a group of individual plots.

Organic cotton production in Paraguay. 1. Some economic limitations for a novel industry. Paraguay, whose small farmers are traditionally cotton growers, has begun to crop and process organic cotton since 2003. An exploratory study was carried out in order to have a better knowledge of the way the organic cotton production has developed and to detect eventual economic limitations. The study was achieved in 2008 during the cotton harvest period by interviewing the actors from the farm to the industrial level. The organic cotton industry was built by a single company in a favorable national (20 years of organic production for a diversity of crops) and international (an increasing demand for organic products, including cotton) context. This single company applied a strategy of creating alliances with NGOs, public authorities and other private operators, in order to increase farm production – by adding new farmers – and textile manufacture and trade worldwide. We detected three kinds of economic limitations. Firstly, organic cotton production still remained largely dependent on the conventional cotton industry for the supply of seed. Secondly, the cumbersome certification process at farm level and its cost associated with increased logistic problems derived from the increase in geographical dispersion of small producers appeared to seriously limit the possibilities for expansion. Thirdly, although the price paid for organic cotton was 12-14% higher in 2008, the obligation for the farmers to sell drier cotton and a longer buying process resulting in delayed cash payments led many farmers to sale a large part of their organic cotton to conventional buyers. We recommend in-depth studies on these three topics to acquire a better knowledge of their extent in terms of intensities and variations, and to propose measures to mitigate them.

The LINTUL-Potato-DSS model uses the linear relationship between radiation intercepted by the crop and radiation-use efficiency (RUE), to calculate dry matter production. The model was developed into a yield forecasting system for processing potatoes based on long-term and actual weather and crop data. The model outcome (Attainable yield, Y) was compared to actual yields (Y) of a summer crop in South Africa and the ratio Y to Y was used for forecasting yield in winter crops. Results showed that accurate forecasts (<20% variation between the actual and forecasted values) could be produced already early in the growing season, and that for the cultivar Innovator, actual and forecasted yields were well correlated ( r = 0.797). Forecasted and observed yields at harvest were not significantly different at the 5% level, P = 0.637 ( t test). Forecasts of tuber number using LINTUL-Potato-DSS were not accurate in the present study and further research is needed on this aspect. It is concluded that the model is a valuable management tool that can be used to produce accurate forecasts of tuber yield from as early as 8 weeks before the final harvest. Since the model was tested with only one cultivar grown in three different growing regions of South Africa, further evaluation using different cultivars and localities is recommended. [ABSTRACT FROM AUTHOR]

This study presents an application of artificial neural network and regression modeling techniques for forecasting grassland dry matter yield. Using data from a field plot experiment on semi-natural grassland in Maribor (Slovenia), the multiple regression and artificial neural network methodologies were employed to explain the patterns of dry matter yield during a 6-year period. On the basis of the two proposed approaches forecasts were conducted for the independent, validation year (6). The results in terms of Theil inequality coefficient, mean absolute error, and correlation coefficient show a better forecasting performance for the artificial neural network (likely due to the non-linear relationships prevailing among regressors and regressand) while relationships between observables can be better explained by regression modeling results. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The data of kharif rice yield and the weather parameters from 1985 to 2009 is used for developing statistical models for three coastal districts of Karnataka. These pre-harvest forecasting models were developed for rice yield forecasts for Dakshin Kannada, Udupi and Uttar Kannada districts respectively. The weather indices like Z21, Z251 and Time were able to forecast the yield of rice for Udupi district. Similarly Z120, Z150 and Z241 were found to be most efficient predictors for Dakshin Kannada district. Only one variable i.e. Z451 was found to be able to forecast the rice yield in Uttar Kannada district. The validation of the model was done for a period of three years from 2010-2012. The forecasting models were able to explain the inter annual variation in the rice production to an extent of 86, 95 and 74% for Dakshin Kannada, Udupi and Uttar Kannada districts respectively. Hence these models can be used to forecast rice yield two months before harvest.

Bud fertility was estimated in two commercial vineyards of Vitis vinifera cv. Tannat in the southern region of Uruguay; it was carried out in two periods: 1983-1986 (essay A) and 2001,2002,2003 (essay B). The information about bud fertility and yield obtained in the essay A was used as a historical series. The essay B begun in the year 2001. In the two essays, two pruning systems were evaluated: Guyot and cordon de Royat. The pruning system has a very important influence on the bud fertility and therefore on the yield. The Guyot type of pruning, showed for all the years involved in the essay a tendency to higher yields, if it is compared to the Cordon de Royat type of pruning. The study of the bud fertility, yield and the pruning type for a vineyard during a number of years, can be used as a tool to predict the harvest volume.