Effect of warming temperatures on US wheat yields

Climate change is expected to increase future temperatures, potentially resulting in reduced crop production in many key production regions. Research quantifying the complex relationship between weather variables and wheat yields is rapidly growing, and recent advances have used a variety of model specifications that differ in how temperature data are included in the statistical yield equation. A unique data set that combines Kansas wheat variety field trial outcomes for 1985–2013 with location-specific weather data is used to analyze the effect of weather on wheat yield using regression analysis. Our results indicate that the effect of temperature exposure varies across the September−May growing season. The largest drivers of yield loss are freezing temperatures in the Fall and extreme heat events in the Spring. We also find that the overall effect of warming on yields is negative, even after accounting for the benefits of reduced exposure to freezing temperatures. Our analysis indicates that there exists a tradeoff between average (mean) yield and ability to resist extreme heat across varieties. More-recently released varieties are less able to resist heat than older lines. Our results also indicate that warming effects would be partially offset by increased rainfall in the Spring. Finally, we find that the method used to construct measures of temperature exposure matters for both the predictive performance of the regression model and the forecasted warming impacts on yields.

Download Full-text

WHEAT YIELDS FOR 50 YEARS AT SWIFT CURRENT, SASKATCHEWAN IN RELATION TO WEATHER

Canadian Journal of Plant Science ◽

10.4141/cjps74-112 ◽

1974 ◽

Vol 54 (4) ◽

pp. 625-650 ◽

Cited By ~ 18

Author(s):

GEO. W. ROBERTSON

Keyword(s):

Crop Production ◽

Global Radiation ◽

Wheat Yield ◽

Triticum Aestivum L ◽

Quadratic Functions ◽

Weather Data ◽

Temperature And Precipitation ◽

Weather Model ◽

Surveillance Programs ◽

Crop Condition

Half a century of wheat yield and weather records at Swift Current in southwestern Saskatchewan were analyzed to determine the response of wheat (Triticum aestivum L.) to changing weather patterns. Weather at Swift Current has undergone subtle but significant changes over the past 50 yr. Earlier years had disturbed conditions: hot, dry periods alternating with cool, wet ones resulting in yield fluctuations ranging from crop failures to maximum values. More recently the weather has been quiet: dry and cool but less variable from year to year. The resulting conditions were more favorable for near-normal but less variable yields. Simple precipitation-based yield–weather models developed two decades ago no longer apply, because temperature and precipitation patterns are currently out of phase relative to earlier conditions. A factorial yield–weather model was used to explain the complex relationship. This involved the summation of the product of several quadratic functions of various weather elements. Those elements considered were precipitation, maximum and minimum temperatures, global radiation estimated from duration of bright sunshine, evaporation from a buried pan, and time as an indicator of advancing technology. One function contained a term for the antecedant crop condition. The most important elements were precipitation for the summer-fallow period and for May, June and August; maximum temperatures for June and July; and global radiation for May. Advances in technology would seem to have very little influence on wheat yield trends after weather trends were accounted for. The model accounted for 73% (r = 0.854) of the yield variability and provided realistic functions for explaining the curvilinear influence of individual weather elements on wheat yield. The model is of a form that is readily adaptable for assessing, at any time during the crop development period, the influence of past and current weather on future expected yield. This could be useful for interpreting weather data in terms of crop production in weather and crop condition surveillance programs.

Download Full-text

Comparison of Lasso and stepwise regression technique for wheat yield prediction

Journal of Agrometeorology ◽

10.54386/jam.v21i2.231 ◽

2021 ◽

Vol 21 (2) ◽

pp. 188-192

Author(s):

SUDHEER KUMAR ◽

S.D. ATTRI ◽

K.K. SINGH

Keyword(s):

Crop Production ◽

Stepwise Regression ◽

Wheat Yield ◽

Forecast Model ◽

Regression Technique ◽

Weather Data ◽

Prediction Errors ◽

Lasso Regression ◽

Statistical Parameters ◽

Forecast Models

Multiple regression approach has been used to forecast the crop production widely. This study has been undertaken to evaluate the performance of stepwise and Lasso (Least absolute shrinkage and selection operator) regression technique in variable selection and development of wheat forecast model for crop yield using weather data and wheat yield for the period of 1984-2015, collected from IARI, New Delhi. Statistical parameters viz. R2, RMSE, and MAPE were 0.81, 195.90 and 4.54 per cent respectively with stepwise regression and 0.95, 99.27, 2.7 percentage, respectively with Lasso regression. Forecast models were validated during 2013-14 and 2014-15. Prediction errors were -8.5 and 10.14 per cent with stepwise and 1.89 and 1.64 percent with the Lasso. This shows that performance of Lasso regression is better than stepwise regression to some extent.

Download Full-text

Use of CERES-Wheat model for wheat yield forecast in central Indo-Gangetic Plains of India

The Journal of Agricultural Science ◽

10.1017/s0021859604004022 ◽

2004 ◽

Vol 142 (1) ◽

pp. 59-70 ◽

Cited By ~ 16

Author(s):

A. S. NAIN ◽

V. K. DADHWAL ◽

T. P. SINGH

Keyword(s):

Simulation Model ◽

Wheat Yield ◽

Uttar Pradesh ◽

Weather Data ◽

Large Area ◽

Data Set ◽

Yield Forecast ◽

Final Yield ◽

Eastern Uttar Pradesh ◽

Technology Trend

A methodology was developed for large area yield forecast using a crop simulation model and a discrete technology trend, and was applied to the coherent wheat yield variability zones of Eastern Uttar Pradesh, India. The approach consisted of three major steps: (a) prediction of technology trend yield using historical yield series of the region; (b) prediction of weather-induced deviation in wheat yield using CERES-Wheat simulation model and relating weather-induced deviation in simulated yield to deviation in observed yield deviations from technology trend; and (c) final yield forecast by incorporating predicted yield deviation in trend predicted yield. The regression coefficients for step (b) were generated using 10 years' data (1984/85–1994/95) and the reliability of the approach was tested on a data set of 5 years' independent data (1995/96–1999/2000). The results showed that this approach could capture year-to-year variability in large area wheat yield with reasonable accuracy. The Root Mean Square Error (RMSE) between observed and predicted yield was reported as 0·098 t/ha for the mean yield of 2·072 t/ha (4·72%). However, the RMSE was slightly higher in the forecasting period in comparison to the calibration period. The use of this methodology for issuing the pre-harvest forecast and the effect of upgrading the technology trend were also studied. The pre-harvest forecasts were made using in-season weather data up to the end of February and climatic-normal for the rest of the wheat-growing season, which showed good agreement with observed wheat yields. The forecasts of wheat yield for the season 1999/2000 were made using the technology trend up to 1994/95 and the updated technology trend up to 1998/99, which showed that the RMSE fell in the latter case, from 4·10 to 2·50%.

Download Full-text

Fungicide Application Affects Nitrogen Utilization Efficiency, Grain Yield, and Quality of Winter Wheat

Agronomy ◽

10.3390/agronomy11071295 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1295

Author(s):

Ahossi Patrice Koua ◽

Mirza Majid Baig ◽

Benedict Chijioke Oyiga ◽

Jens Léon ◽

Agim Ballvora

Keyword(s):

Synergistic Effect ◽

Grain Yield ◽

Crop Production ◽

Agronomic Traits ◽

Yellow Rust ◽

Wheat Yield ◽

Utilization Efficiency ◽

High Nitrogen ◽

Available N ◽

Fungicide Application

Nitrogen (N) is a vital component of crop production. Wheat yield varies significantly under different soil available N. Knowing how wheat responds to or interacts with N to produce grains is essential in the selection of N use efficient cultivars. We assessed in this study variations among wheat genotypes for productivity-related traits under three cropping systems (CS), high-nitrogen with fungicide (HN-WF), high-nitrogen without fungicide (HN-NF) and low-nitrogen without fungicide (LN-NF) in the 2015, 2016 and 2017 seasons. ANOVA results showed genotypes, CS, and their interactions significantly affected agronomic traits. Grain yield (GY) increased with higher leaf chlorophyll content, importantly under CS without N and fungicide supply. Yellow rust disease reduced the GY by 20% and 28% in 2015 and 2016, respectively. Moreover, averaged over growing seasons, GY was increased by 23.78% under CS with N supply, while it was greatly increased, by 52.84%, under CS with both N and fungicide application, indicating a synergistic effect of N and fungicide on GY. Fungicide supply greatly improved the crop ability to accumulate N during grain filling, and hence the grain protein content. Recently released cultivars outperformed the older ones in most agronomic traits including GY. Genotype performance and stability analysis for GY production showed differences in their stability levels under the three CS. The synergistic effect of nitrogen and fungicide on grain yield (GY) and the differences in yield stability levels of recently released wheat cultivars across three CS found in this study suggest that resource use efficiency can be improved via cultivar selection for targeted CS.

Download Full-text

Nitrogen form, time and rate of application, and nitrification inhibitor effects on crop production

Canadian Journal of Plant Science ◽

10.4141/cjps2013-205 ◽

2014 ◽

Vol 94 (2) ◽

pp. 425-432 ◽

Cited By ~ 4

Author(s):

R. E. Karamanos ◽

K. Hanson ◽

F. C. Stevenson

Keyword(s):

Crop Production ◽

Protein Concentration ◽

Wheat Yield ◽

Nitrification Inhibitor ◽

N Fertilizer ◽

Nitrogen Form ◽

Anhydrous Ammonia ◽

N Concentration ◽

Fertilizer Rates ◽

Better Than

Karamanos, R., Hanson, K. and Stevenson, F. C. 2014. Nitrogen form, time and rate of application, and nitrification inhibitor effects on crop production. Can. J. Plant Sci. 94: 425–432. Nitrogen management options for anhydrous ammonia (NH3) and urea were compared in a barley–wheat–canola–wheat cropping sequence (2007–2010) at Watrous and Lake Lenore, SK. The treatment design included a factorial arrangement of N fertilizer form (NH3versus urea), nitrification inhibitor application, time of N application (mid-September, mid- to late October, and spring) and four N fertilizer rates (0, 40, 80 and 120 kg ha−1). Anhydrous ammonia applications at 40 kg N ha−1in 2008 (fall) and in 2010 (all times of application) resulted in wheat yield reductions relative to the same applications for urea. For wheat years, yield was reduced for both fall versus spring N fertilizer applications, when no nitrification inhibitor was applied and the inclusion of nitrification inhibitor maintained wheat yield at similar levels across all times of N fertilizer applications, regardless of form. Protein concentration was approximately 2 g kg−1greater with urea compared with NH3at both sites in 2008 and only at Watrous in 2010. Also, early versus late fall N fertilizer applications consistently increased N concentration of grain only for the 40 and/or 80 kg N ha−1rates. Effects of nitrification inhibitor on N concentration were not frequent and appeared to be minimal. Urea had greater agronomic efficiency (AE) than NH3at the lower N fertilizer rates. The nitrification inhibitor had a positive effect on wheat AE only for early fall N fertilizer applications. It can be concluded that for maximum yields NH3or urea will be suitable if applied at rates of 80 kg N ha−1and greater. If N fertilizer is applied at 40 kg N ha−1, especially in fall without inhibitor, urea is better. In terms of protein concentration for wheat, urea seemed to better than NH3and fall was better than spring application.

Download Full-text

Nowcasting heavy precipitation over the Netherlands using a 13-year radar archive: a machine learning approach

10.5194/egusphere-egu21-12814 ◽

2021 ◽

Author(s):

Eva van der Kooij ◽

Marc Schleiss ◽

Riccardo Taormina ◽

Francesco Fioranelli ◽

Dorien Lugt ◽

...

Keyword(s):

Machine Learning ◽

The Netherlands ◽

Heavy Rainfall ◽

Predictive Performance ◽

Heavy Precipitation ◽

Early Warning Systems ◽

Training Data ◽

Short Term ◽

Data Set ◽

Radar Images

Accurate short-term forecasts, also known as nowcasts, of heavy precipitation are desirable for creating early warning systems for extreme weather and its consequences, e.g. urban flooding. In this research, we explore the use of machine learning for short-term prediction of heavy rainfall showers in the Netherlands.We assess the performance of a recurrent, convolutional neural network (TrajGRU) with lead times of 0 to 2 hours. The network is trained on a 13-year archive of radar images with 5-min temporal and 1-km spatial resolution from the precipitation radars of the Royal Netherlands Meteorological Institute (KNMI). We aim to train the model to predict the formation and dissipation of dynamic, heavy, localized rain events, a task for which traditional Lagrangian nowcasting methods still come up short.We report on different ways to optimize predictive performance for heavy rainfall intensities through several experiments. The large dataset available provides many possible configurations for training. To focus on heavy rainfall intensities, we use different subsets of this dataset through using different conditions for event selection and varying the ratio of light and heavy precipitation events present in the training data set and change the loss function used to train the model.To assess the performance of the model, we compare our method to current state-of-the-art Lagrangian nowcasting system from the pySTEPS library, like S-PROG, a deterministic approximation of an ensemble mean forecast. The results of the experiments are used to discuss the pros and cons of machine-learning based methods for precipitation nowcasting and possible ways to further increase performance.

Download Full-text

Comparing predictive performance of general regression neural network (GRNN) and hedonic regression model for factors affecting housing prices in “Pune-India”

International Journal of Housing Markets and Analysis ◽

10.1108/ijhma-01-2021-0003 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Abhijat Arun Abhyankar ◽

Harish Kumar Singla

Keyword(s):

Neural Network ◽

Regression Model ◽

Multivariate Regression ◽

Housing Prices ◽

Predictive Performance ◽

General Regression Neural Network ◽

Multivariate Regression Model ◽

Data Set ◽

Content Type ◽

General Regression

Purpose The purpose of this study is to compare the predictive performance of the hedonic multivariate regression model with the probabilistic neural network (PNN)-based general regression neural network (GRNN) model of housing prices in “Pune-India.” Design/methodology/approach Data on 211 properties across “Pune city-India” is collected. The price per square feet is considered as a dependent variable whereas distances from important landmarks such as railway station, fort, university, airport, hospital, temple, parks, solid waste site and stadium are considered as independent variables along with a dummy for amenities. The data is analyzed using a hedonic type multivariate regression model and GRNN. The GRNN divides the entire data set into two sets, namely, training set and testing set and establishes a functional relationship between the dependent and target variables based on the probability density function of the training data (Alomair and Garrouch, 2016). Findings While comparing the performance of the hedonic multivariate regression model and PNN-based GRNN, the study finds that the output variable (i.e. price) has been accurately predicted by the GRNN model. All the 42 observations of the testing set are correctly classified giving an accuracy rate of 100%. According to Cortez (2015), a value close to 100% indicates that the model can correctly classify the test data set. Further, the root mean square error (RMSE) value for the final testing for the GRNN model is 0.089 compared to 0.146 for the hedonic multivariate regression model. A lesser value of RMSE indicates that the model contains smaller errors and is a better fit. Therefore, it is concluded that GRNN is a better model to predict the housing price functions. The distance from the solid waste site has the highest degree of variable senstivity impact on the housing prices (22.59%) followed by distance from university (17.78%) and fort (17.73%). Research limitations/implications The study being a “case” is restricted to a particular geographic location hence, the findings of the study cannot be generalized. Further, as the objective of the study is restricted to just to compare the predictive performance of two models, it is felt appropriate to restrict the scope of work by focusing only on “location specific hedonic factors,” as determinants of housing prices. Practical implications The study opens up a new dimension for scholars working in the field of housing prices/valuation. Authors do not rule out the use of traditional statistical techniques such as ordinary least square regression but strongly recommend that it is high time scholars use advanced statistical methods to develop the domain. The application of GRNN, artificial intelligence or other techniques such as auto regressive integrated moving average and vector auto regression modeling helps analyze the data in a much more sophisticated manner and help come up with more robust and conclusive evidence. Originality/value To the best of the author’s knowledge, it is the first case study that compares the predictive performance of the hedonic multivariate regression model with the PNN-based GRNN model for housing prices in India.

Download Full-text

StackBC: Deep learning and transfer learning techniques based stacking approach for accurate Invasive Ductal Carcinoma classification using histology images

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-212240 ◽

2022 ◽

pp. 1-12

Author(s):

Amin Ul Haq ◽

Jian Ping Li ◽

Samad Wali ◽

Sultan Ahmad ◽

Zafar Ali ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Transfer Learning ◽

Invasive Ductal Carcinoma ◽

Ductal Carcinoma ◽

Early Recognition ◽

Predictive Performance ◽

Operating Characteristics ◽

Data Set ◽

Learning Techniques

Artificial intelligence (AI) based computer-aided diagnostic (CAD) systems can effectively diagnose critical disease. AI-based detection of breast cancer (BC) through images data is more efficient and accurate than professional radiologists. However, the existing AI-based BC diagnosis methods have complexity in low prediction accuracy and high computation time. Due to these reasons, medical professionals are not employing the current proposed techniques in E-Healthcare to effectively diagnose the BC. To diagnose the breast cancer effectively need to incorporate advanced AI techniques based methods in diagnosis process. In this work, we proposed a deep learning based diagnosis method (StackBC) to detect breast cancer in the early stage for effective treatment and recovery. In particular, we have incorporated deep learning models including Convolutional neural network (CNN), Long short term memory (LSTM), and Gated recurrent unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, data augmentation and transfer learning techniques have been incorporated for data set balancing and for effective training the model. To further improve the predictive performance of model we used stacking technique. Among the three base classifiers (CNN, LSTM, GRU) the predictive performance of GRU are better as compared to individual model. The GRU is selected as a meta classifier to distinguish between Non-IDC and IDC breast images. The method Hold-Out has been incorporated and the data set is split into 90% and 10% for training and testing of the model, respectively. Model evaluation metrics have been computed for model performance evaluation. To analyze the efficacy of the model, we have used breast histology images data set. Our experimental results demonstrated that the proposed StackBC method achieved improved performance by gaining 99.02% accuracy and 100% area under the receiver operating characteristics curve (AUC-ROC) compared to state-of-the-art methods. Due to the high performance of the proposed method, we recommend it for early recognition of breast cancer in E-Healthcare.

Download Full-text

Quantification of leaf greenness and leaf spectral profile in plant diagnosis using an optical scanner

Ciência e Agrotecnologia ◽

10.1590/s1413-70542012000300006 ◽

2012 ◽

Vol 36 (3) ◽

pp. 309-317 ◽

Cited By ~ 4

Author(s):

Ryoichi Doi

Keyword(s):

Spectral Data ◽

Crop Production ◽

Response Pattern ◽

Quadratic Growth ◽

Spectral Profile ◽

Growth Data ◽

Data Set ◽

Optical Scanner ◽

Color Scale ◽

Management Measures

Observation of leaf spectral profile (color) enables suitable management measures to be taken for crop production. An optical scanner was used: 1) to obtain an equation to determine the greenness of plant leaves and 2) to examine the power to discriminate among plants grown under different nutritional conditions. Sweet basil seedlings grown on vermiculite were supplemented with one-fifth-strength Hoagland solutions containing 0, 0.2, 1, 5, 20, and 50 mM NH4+. The 5 mM treatment resulted in the greatest leaf and shoot weights, indicating a quadratic growth response pattern to the NH4+ gradient. An equation involving b*, black and green to describe the greenness of leaves was provided by the spectral profiling of a color scale for rice leaves as the standard. The color scale values for the basil leaves subjected to 0.2 and 1 mM NH4+ treatments were 1.00 and 1.12, respectively. The other treatments resulted in significantly greater values of 2.25 to 2.42, again indicating a quadratic response pattern. Based on the spectral data set consisting of variables of red-green-blue and other color models and color scale values, in discriminant analysis, 81% of the plants were correctly classified into the six NH4+ treatment groups. Combining the spectral data set with the growth data set consisting of leaf and shoot weights, 92% of the plant samples were correctly classified whereas, using the growth data set, only 53% of plants were correctly classified. Therefore, the optical scanning of leaves and the use of spectral profiles helped plant diagnosis when biomass measurements were not effective.

Download Full-text

Effects of the Foliar Application of Potassium Fertilizer on the Grain Protein and Dough Quality of Wheat

Agronomy ◽

10.3390/agronomy11091749 ◽

2021 ◽

Vol 11 (9) ◽

pp. 1749

Author(s):

Xiaoyan Gu ◽

Yang Liu ◽

Na Li ◽

Yihong Liu ◽

Deqiang Zhao ◽

...

Keyword(s):

Protein Content ◽

Foliar Application ◽

Wheat Variety ◽

Wheat Yield ◽

Gluten Protein ◽

Processing Quality ◽

Potassium Fertilizer ◽

Flowering Stage ◽

Yield And Quality ◽

Gluten Content

Potassium (K) has a significant effect on wheat yield and quality. Owing to the limitations of irrigation and production costs, soil-based applications of potassium fertilizer are not performed in wheat production on the Loess Plateau of China. In the late growth stage of wheat, potassium deficiency occurs even under sufficient nitrogen/phosphorus (N/P) levels, so it is necessary to supplement potassium through foliar spraying. However, there are few studies on the effect of the foliar application of potassium fertilizer (KFA) on wheat quality. Field experiments were conducted at two experimental sites for 2 years to study the effects of different potassium fertilizer application levels and periods on wheat yield and quality. The results showed that KFA had no significant effect on the yield of the wheat variety Xinong 20 (XN20) but increased the yield of the wheat variety Xiaoyan 22 (XY22). The improvement effect of KFA on the wet gluten content and stabilization time (ST) of XN20 was better than that on these parameters of XY22, while the sedimentation value (SV) and formation time (FT) showed the opposite trend. KFA significantly reduced the albumin content of the two varieties but had no significant effect on the globulin content. Compared with that at the other two stages, the potassium application in the form of potash fertilizer spray at a concentration of 60 mmol L−1 (K2) at the flowering stage (BBCH 65) significantly increased the protein content, wet gluten content, SV and gluten protein content in XN20 grains, whereas the application at 10 days after flowering (AA10, BBCH 71) at the K2 concentration was more beneficial to prolonging the dough FT. For XY22, the application of potassium fertilizer at the K2 concentration at the flowering stage increased the wet gluten and gluten protein levels and dough development time. There were significant genotypic differences in the composition and content of HMW-GS between the two varieties. KFA significantly increased the levels of the 1, 7 + 8, and 4 + 12 subunits in XN20 and the 1 subunit in XY22, but had no significant effect on the 2 + 12 subunit in XY22. Partial least squares path modelling (PLS-PM) analysis showed that the processing quality indexes (SV, FT, ST) and gluten protein and HMW-GS levels were regulated by the potassium fertilizer foliar spraying stage and concentration and revealed in part that KFA affected the processing quality by affecting the HMW-GS content.

Download Full-text