scholarly journals Prediction of municipality-level winter wheat yield based on meteorological data using machine learning in Hokkaido, Japan

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258677
Author(s):  
Keach Murakami ◽  
Seiji Shimoda ◽  
Yasuhiro Kominami ◽  
Manabu Nemoto ◽  
Satoshi Inoue
Keyword(s):  
Machine Learning ◽  
Air Temperature ◽  
Meteorological Data ◽  
Wheat Yield ◽  
Null Model ◽  
Grain Filling ◽  
Winter Wheat Yield ◽  
Wet Climate ◽  
Grain Filling Period ◽  
Minimum Air Temperature

This study analyzed meteorological constraints on winter wheat yield in the northern Japanese island, Hokkaido, and developed a machine learning model to predict municipality-level yields from meteorological data. Compared to most wheat producing areas, this island is characterized by wet climate owing to greater annual precipitation and abundant snowmelt water supply in spring. Based on yield statistics collected from 119 municipalities for 14 years (N = 1,516) and high-resolution surface meteorological data, correlation analyses showed that precipitation, daily minimum air temperature, and irradiance during the grain-filling period had significant effects on the yield throughout the island while the effect of snow depth in early winter and spring was dependent on sites. Using 10-d mean meteorological data within a certain period between seeding and harvest as predictor variables and one-year-leave-out cross-validation procedure, performance of machine learning models based on neural network (NN), random forest (RF), support vector machine regression (SVR), partial least squares regression (PLS), and cubist regression (CB) were compared to a multiple linear regression model (MLR) and a null model that returns an average yield of the municipality. The root mean square errors of PLS, SVR, and RF were 872, 982, and 1,024 kg ha−1 and were smaller than those of MLR (1,068 kg ha−1) and null model (1,035 kg ha−1). These models outperformed the controls in other metrics including Pearson’s correlation coefficient and Nash-Sutcliffe efficiency. Variable importance analysis on PLS indicated that minimum air temperature and precipitation during the grain-filling period had major roles in the prediction and excluding predictors in this period (i.e. yield forecast with a longer lead-time) decreased forecast performance of the models. These results were consistent with our understanding of meteorological impacts on wheat yield, suggesting usefulness of explainable machine learning in meteorological crop yield prediction under wet climate.

scholarly journals Influence of meteorological parameters on wheat yield under different sowing conditions

MAUSAM ◽  
2022 ◽  
Vol 73 (1) ◽  
pp. 161-172
Author(s):  
ANANTA VASHISTH ◽  
DEBASISH ROY ◽  
AVINASH GOYAL ◽  
P. KRISHNAN
Keyword(s):  
Relative Humidity ◽  
Soil Temperature ◽  
Air Temperature ◽  
Field Experiments ◽  
Wheat Yield ◽  
Weather Condition ◽  
Grain Filling ◽  
Crop Growth ◽  
Leaf Water ◽  
Growth Stages

Field experiments were conducted on the research farm of IARI, New Delhi during Rabi 2016-17 and 2017-18. Three varieties of wheat (PBW-723, HD-2967 and HD-3086) were sown on three different dates for generating different weather condition during various phenological stages of crop. Results showed that during early crop growth stages soil moisture had higher value and soil temperature had lower value and with progress of crop growth stage, the moisture in the upper layer decreased and soil temperature increased significantly as compared to the bottom layers. During tillering and jointing stage, air temperature within canopy was more and relative humidity was less while during flowering and grain filling stage, air temperature within canopy was less and relative humidity was more in timely sown crop as compared to late and very late sown crop. Radiation use efficiency and relative leaf water content had significantly higher value while leaf water potential had lower value in timely sown crop followed by late and very late sown crop. Yield had higher value in HD-3086 followed by HD-2967 and PBW-723 in all weather conditions. Canopy air temperature difference had positive value in very late sown crop particularly during flowering and grain-filling stages. This reflects in the yield. Yield was more in timely sown crop as compared to late and very late sown crop.  

scholarly journals Relationship Between Phenological and Meteorological Data as an Important Input Into Spring Barley Phenological Model

2019 ◽  
Vol 67 (3) ◽  
pp. 679-688
Author(s):  
Lenka Hájková ◽  
Martin Možný ◽  
Věra Kožnarová ◽  
Lenka Bartošová ◽  
Zdeněk Žalud
Keyword(s):  
Meteorological Data ◽  
Spring Barley ◽  
Meteorological Parameter ◽  
Grain Filling ◽  
Phenological Stage ◽  
Phenological Stages ◽  
Phenological Model ◽  
Average Value ◽  
Precipitation Total ◽  
Grain Filling Period

In this study, phenological and meteorological data have been used to interpret the relationship and influence of weather on current phenological stages of spring barley. The analyses were focused mainly on the stages closely connected with yield and grain filling period – tillering (BBCH 21), heading (BBCH 55) and yellow ripeness (BBCH 85). The aims of this paper were to: (1) calculate the trend in phenological development of spring barley from CHMI phenological stations in period 1991 – 2012 at different climatic zones; (2) evaluate the trend in number of days between phenological stages; (3) evaluate the sums of growing degree days above threshold above 5 °C (GDD) and precipitation totals to phenophase onset calculated since the phenological stage of emergence (BBCH 10); (4) calculate Pearson’s correlation coefficient (PCC) between phenological stage and meteorological parameter. The highest positive PCC was found between GDD and phenological stages of heading and yellow ripeness at Doksany and Strážnice stations situated in lowlands. The average value of GDD to phenological stage heading is within the range from 418.4 to 500.1 °C. The sums of precipitation totals fluctuate from 73.9 mm (Doksany station) to 123.2 mm (Chrastava station). The results of this study suggest that GDD can be a more suitable parameter for phenological model of spring barley development than precipitation total.

Canopy temperature depression at grain filling correlates to winter wheat yield in the U.S. Southern High Plains

2018 ◽  
Vol 217 ◽  
pp. 11-19 ◽  
Author(s):  
Sushil Thapa ◽  
Kirk E. Jessup ◽  
Gautam P. Pradhan ◽  
Jackie C. Rudd ◽  
Shuyu Liu ◽  
...  
Keyword(s):  
Winter Wheat ◽  
Wheat Yield ◽  
Canopy Temperature ◽  
Grain Filling ◽  
High Plains ◽  
Southern High Plains ◽  
Canopy Temperature Depression ◽  
Winter Wheat Yield ◽  
Temperature Depression ◽  
The U.S

scholarly journals Winter Wheat Yield Prediction Using Convolutional Neural Networks from Environmental and Phenological Data

2021 ◽  
Author(s):  
Amit Kumar Srivast ◽  
Nima Safaei ◽  
Saeed Khaki ◽  
Gina Lopez ◽  
Wenzhi Zeng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Winter Wheat ◽  
Crop Yield ◽  
Wheat Yield ◽  
Yield Prediction ◽  
Learning Models ◽  
Winter Wheat Yield ◽  
Machine Learning Models

Abstract Crop yield forecasting depends on many interactive factors including crop genotype, weather, soil, and management practices. This study analyzes the performance of machine learning and deep learning methods for winter wheat yield prediction using extensive datasets of weather, soil, and crop phenology. We propose a convolutional neural network (CNN) which uses the 1-dimentional convolution operation to capture the time dependencies of environmental variables. The proposed CNN, evaluated along with other machine learning models for winter wheat yield prediction in Germany, outperformed all other models tested. To address the seasonality, weekly features were used that explicitly take soil moisture and meteorological events into account. Our results indicated that nonlinear models such as deep learning models and XGboost are more effective in finding the functional relationship between the crop yield and input data compared to linear models and deep neural networks had a higher prediction accuracy than XGboost. One of the main limitations of machine learning models is their black box property. Therefore, we moved beyond prediction and performed feature selection, as it provides key results towards explaining yield prediction (variable importance by time). As such, our study indicates which variables have the most significant effect on winter wheat yield.

scholarly journals Simulation of wheat yield by nitrogen and nonlinearity of environmental conditions

2020 ◽  
Vol 24 (1) ◽  
pp. 44-51
Author(s):  
Ana P. B. Trautmann ◽  
José A. G. da Silva ◽  
Manuel O. Binelo ◽  
Antonio C. Valdiero ◽  
Luana Henrichsen ◽  
...  
Keyword(s):  
Fuzzy Logic ◽  
Air Temperature ◽  
Block Design ◽  
Wheat Yield ◽  
Grain Filling ◽  
Phenological Stage ◽  
Southern Brazil ◽  
Wheat Grain ◽  
Nitrogen Use ◽  
Randomized Block Design

ABSTRACT Fuzzy logic can simulate wheat productivity by assisting crop predictability. The objective of the study is the use of fuzzy logic to simulate wheat yield in the conditions of nitrogen use, together with the effects of air temperature and rainfall, in the main cereal succession systems in Southern Brazil. The study was conducted in the years 2014, 2015 and 2016, in Augusto Pestana, RS, Brazil. The experimental design was a randomized block design with four repetitions in a 4 x 3 factorial scheme for N-fertilizer doses (0, 30, 60, 120 kg ha-1) and nutrient supply forms [100% in phenological stage V3 (third expanded leaf); (70%/30%) in the phenological stage V3/V6 (third and sixth expanded leaf) and; fractionated (70%/30%) at the phenological stage V3/E (third expanded leaf and beginning of grain filling)], respectively, in the soybean/wheat and corn/wheat systems. The pertinence functions and the linguistic values established for the input and output variables are adequate for the use of fuzzy logic. Fuzzy logic simulates wheat grain yield efficiently in the conditions of nitrogen use with air temperature and rainfall in crop systems.

scholarly journals Effect of meteorological factors on influenza-like illness from 2012 to 2015 in Huludao, a northeastern city in China

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e6919 ◽  
Author(s):  
Ying-Long Bai ◽  
De-Sheng Huang ◽  
Jing Liu ◽  
De-Qiang Li ◽  
Peng Guan
Keyword(s):  
Relative Humidity ◽  
Vapor Pressure ◽  
Air Temperature ◽  
Meteorological Factors ◽  
Meteorological Data ◽  
Lag Time ◽  
Temperature Minimum ◽  
The Relationship ◽  
Maximum Air Temperature ◽  
Minimum Air Temperature

Background This study aims to describe the epidemiological patterns of influenza-like illness (ILI) in Huludao, China and seek scientific evidence on the link of ILI activity with weather factors. Methods Surveillance data of ILI cases between January 2012 and December 2015 was collected in Huludao Central Hospital, meteorological data was obtained from the China Meteorological Data Service Center. Generalized additive model (GAM) was used to seek the relationship between the number of ILI cases and the meteorological factors. Multiple Smoothing parameter estimation was made on the basis of Poisson distribution, where the number of weekly ILI cases was treated as response, and the smoothness of weather was treated as covariates. Lag time was determined by the smallest Akaike information criterion (AIC). Smoothing coefficients were estimated for the prediction of the number of ILI cases. Results A total of 29, 622 ILI cases were observed during the study period, with children ILI cases constituted 86.77%. The association between ILI activity and meteorological factors varied across different lag periods. The lag time for average air temperature, maximum air temperature, minimum air temperature, vapor pressure and relative humidity were 2, 2, 1, 1 and 0 weeks, respectively. Average air temperature, maximum air temperature, minimum air temperature, vapor pressure and relative humidity could explain 16.5%, 9.5%, 18.0%, 15.9% and 7.7% of the deviance, respectively. Among the temperature indexes, the minimum temperature played the most important role. The number of ILI cases peaked when minimum temperature was around −13 °C in winter and 18 °C in summer. The number of cases peaked when the relative humidity was equal to 43% and then began to decrease with the increase of relative humidity. When the humidity exceeded 76%, the number of ILI cases began to rise. Conclusions The present study first analyzed the relationship between meteorological factors and ILI cases with special consideration of the length of lag period in Huludao, China. Low air temperature and low relative humidity (cold and dry weather condition) played a considerable role in the epidemic pattern of ILI cases. The trend of ILI activity could be possibly predicted by the variation of meteorological factors.

Prediction of temperatures in cattle dung for estimating development times of coprophilous organisms

1988 ◽  
Vol 78 (2) ◽  
pp. 235-240 ◽  
Author(s):  
J. N. Matthiessen ◽  
M. J. Palmer
Keyword(s):  
Air Temperature ◽  
Meteorological Data ◽  
Maximum Temperature ◽  
Daily Maximum Temperature ◽  
Threshold Temperature ◽  
Cattle Dung ◽  
Daily Maximum ◽  
Daily Minimum ◽  
Maximum Temperatures ◽  
Minimum Air Temperature

AbstractIn studies in Western Australia, temperatures in air and one- and two-litre pads of cattle dung set out weekly and ranging from one to 20 days old were measured hourly for 438 days over all seasons, producing 1437 day x dung-pad observations. Daily maximum temperatures (and hence thermal accumulation) in cattle dung pads could not be accurately predicted using meteorological data alone. An accurate predictor of daily maximum dung temperature, using multiple regression analysis, required measurement of the following factors: maximum air temperature, hours of sunshine, rainfall, a seasonal factor (the day number derived from a linear interpolation of day number from day 0 at the winter solstice to day 182 at the preceding and following summer solstices) and a dung-pad age-specific intercept term, giving an equation that explained a 91·4% of the variation in maximum dung temperature. Daily maximum temperature in two-litre dung pads was 0·6°C cooler than in one-litre pads. Daily minimum dung temperature equalled minimum air temperature, and daily minimum dung temperatures occurred at 05.00 h and maximum temperatures at 14.00 h for one-litre and 14.30 h for two-litre pads. Thus, thermal summation in a dung pad above any threshold temperature can be computed using a skewed sine curve fitted to daily minimum air temperature and the calculated maximum dung temperature.

scholarly journals Estimating Farm Wheat Yields from NDVI and Meteorological Data

Agronomy ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 946
Author(s):  
Astrid Vannoppen ◽  
Anne Gobin
Keyword(s):  
Winter Wheat ◽  
Crop Yield ◽  
Meteorological Data ◽  
Wheat Yield ◽  
Model Performance ◽  
Weather Conditions ◽  
Current Data ◽  
Monthly Precipitation ◽  
Empirical Modelling ◽  
Winter Wheat Yield

Information on crop yield at scales ranging from the field to the global level is imperative for farmers and decision makers. The current data sources to monitor crop yield, such as regional agriculture statistics, are often lacking in spatial and temporal resolution. Remotely sensed vegetation indices (VIs) such as NDVI are able to assess crop yield using empirical modelling strategies. Empirical NDVI-based crop yield models were evaluated by comparing the model performance with similar models used in different regions. The integral NDVI and the peak NDVI were weak predictors of winter wheat yield in northern Belgium. Winter wheat (Triticum aestivum) yield variability was better predicted by monthly precipitation during tillering and anthesis than by NDVI-derived yield proxies in the period from 2016 to 2018 (R2 = 0.66). The NDVI series were not sensitive enough to yield affecting weather conditions during important phenological stages such as tillering and anthesis and were weak predictors in empirical crop yield models. In conclusion, winter wheat yield modelling using NDVI-derived yield proxies as predictor variables is dependent on the environment.

scholarly journals Effect of Magnesium Fertilization Systems on Grain Yield Formation by Winter Wheat (Triticum aestivum L.) during the Grain-Filling Period

Agronomy ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 12
Author(s):  
Witold Grzebisz ◽  
Jarosław Potarzycki
Keyword(s):  
Grain Yield ◽  
Plant Material ◽  
Dry Matter ◽  
Wheat Yield ◽  
Grain Filling ◽  
Triticum Aestivum L ◽  
Dry Matter Partitioning ◽  
Wheat Growth ◽  
Grain Filling Period ◽  
Yield Formation

The application of magnesium significantly affects the components of the wheat yield and the dry matter partitioning in the grain-filling period (GFP). This hypothesis was tested in 2013, 2014, and 2015. A two-factorial experiment with three rates of magnesium (0, 25, 50 kg ha−1) and four stages of Mg foliar fertilization (without, BBCH 30, 49/50, two-stage) was carried out. Plant material collected at BBCH: 58, 79, 89 was divided into leaves, stems, ears, chaff, and grain. The wheat yield increased by 0.5 and 0.7 t ha−1 in response to the soil and foliar Mg application. The interaction of both systems gave + 0.9 t ha−1. The Mg application affected the grain yield by increasing grain density (GD), wheat biomass at the onset of wheat flowering, durability of leaves in GFP, and share of remobilized dry matter (REQ) in the grain yield. The current photosynthesis accounted for 66% and the REQ for 34%. The soil-applied Mg increased the REQ share in the grain yield to over 50% in 2014 and 2015. The highest yield is possible, but provided a sufficiently high GD, and a balanced share of both assimilate sources in the grain yield during the maturation phase of wheat growth.

Sign in / Sign up

Export Citation Format

Share Document