Improved Yield Prediction of Ratoon Rice Using Unmanned Aerial Vehicle-Based Multi-Temporal Feature Method

Pre-harvest yield prediction of ratoon rice is critical for guiding crop interventions in precision agriculture.However,the unique agronomic practice(i.e.,varied stubble height treatment)in rice ratooning could lead to inconsistent rice phenology,which had a significant impact on yield prediction of ratoon rice.Multi-temporal unmanned aerial vehicle(UAV)-based remote sensing can likely monitor ratoon rice productivity and reflect maximum yield potential across growing seasons for improving the yield prediction compared with previous methods.Thus,in this study,we explored the performance of combination of agronomic practice information(API)and single-phase,multi-spectral features[vegetation indices(VIs)and texture(Tex)features]in predicting ratoon rice yield,and developed a new UAV-based method to retrieve yield formation process by using multi-temporal features which were effective in improving yield forecasting accuracy of ratoon rice.The results showed that the integrated use of VIs,Tex and API(VIs&Tex+API)improved the accuracy of yield prediction than single-phase UAV imagery-based feature,with the panicle initiation stage being the best period for yield prediction(R^(2) as 0.732,RMSE as 0.406,RRMSE as 0.101).More importantly,compared with previous multi-temporal UAV-based methods,our proposed multi-temporal method(multi-temporal model VIs&Tex:R^(2) as 0.795,RMSE as 0.298,RRMSE as 0.072)can increase R^(2) by 0.020-0.111 and decrease RMSE by 0.020-0.080 in crop yield forecasting.This study provides an effective method for accurate pre-harvest yield prediction of ratoon rice in precision agriculture,which is of great significance to take timely means for ensuring ratoon rice production and food security.

Multimodal Machine Learning Based Crop Recommendation and Yield Prediction Model

Agriculture plays a vital role in the Indian economy.Crop recommen-dation for a specific region is a tedious process as it can be affected by various variables such as soil type and climatic parameters.At the same time,crop yield prediction was based on several features like area,irrigation type,temperature,etc.The recent advancements of artificial intelligence(AI)and machine learning(ML)models pave the way to design effective crop recommendation and crop pre-diction models.In this view,this paper presents a novel Multimodal Machine Learning Based Crop Recommendation and Yield Prediction(MMML-CRYP)technique.The proposed MMML-CRYP model mainly focuses on two processes namely crop recommendation and crop prediction.At the initial stage,equilibrium optimizer(EO)with kernel extreme learning machine(KELM)technique is employed for effectual recommendation of crops.Next,random forest(RF)tech-nique was executed for predicting the crop yield accurately.For reporting the improved performance of the MMML-CRYP system,a wide range of simulations were carried out and the results are investigated using benchmark dataset.Experi-mentation outcomes highlighted the significant performance of the MMML-CRYP approach on the compared approaches with maximum accuracy of 97.91%.

Ensemble learning prediction of soybean yields in China based on meteorological data

The accurate prediction of soybean yield is of great significance for agricultural production, monitoring and early warning.Although previous studies have used machine learning algorithms to predict soybean yield based on meteorological data,it is not clear how different models can be used to effectively separate soybean meteorological yield from soybean yield in various regions. In addition, comprehensively integrating the advantages of various machine learning algorithms to improve the prediction accuracy through ensemble learning algorithms has not been studied in depth. This study used and analyzed various daily meteorological data and soybean yield data from 173 county-level administrative regions and meteorological stations in two principal soybean planting areas in China(Northeast China and the Huang–Huai region), covering 34 years.Three effective machine learning algorithms(K-nearest neighbor, random forest, and support vector regression) were adopted as the base-models to establish a high-precision and highly-reliable soybean meteorological yield prediction model based on the stacking ensemble learning framework. The model's generalizability was further improved through 5-fold crossvalidation, and the model was optimized by principal component analysis and hyperparametric optimization. The accuracy of the model was evaluated by using the five-year sliding prediction and four regression indicators of the 173 counties, which showed that the stacking model has higher accuracy and stronger robustness. The 5-year sliding estimations of soybean yield based on the stacking model in 173 counties showed that the prediction effect can reflect the spatiotemporal distribution of soybean yield in detail, and the mean absolute percentage error(MAPE) was less than 5%. The stacking prediction model of soybean meteorological yield provides a new approach for accurately predicting soybean yield.

A Hybrid Approach of TLBO and EBPNN for Crop YieldPrediction Using Spatial Feature Vectors

The prediction of crop yield is one of the important factor and also challenging,to predict the future crop yield based on various criteria’s.Many advanced technologies are incorporated in the agricultural processes,which enhances the crop yield production efficiency.The process of predicting the crop yield can be done by taking agriculture data,which helps to analyze and make important decisions before and during cultivation.This paper focuses on the prediction of crop yield,where two models of machine learning are developed for this work.One is Modified Convolutional Neural Network(MCNN),and the other model is TLBO(Teacher Learning Based Optimization)-a Genetic algorithm which reduces the input size of data.In this work,some spatial information used for analysis is the Normalized Difference Vegetation Index,Standard Precipitation Index and Vegetation Condition Index.TLBO finds some best feature value set in the data that represents the specific yield of the crop.So,these selected feature valued set is passed in the Error Back Propagation Neural Network for learning.Here,the training was done in such a way that all set of features were utilized in pair with their yield value as output.For increasing the reliability of the work whole experiment was done on a real dataset from Madhya Pradesh region of country India.The result shows that the proposed model has overcome various evaluation parameters on different scales as compared to previous approaches adopted by researchers.

Combining machine learning,space-time cloud restoration and phenology for farm-level wheat yield prediction

Though studies showed the potential of high-resolution optical sensors for crop yield prediction,several factors have limited their wider application.The main factors are obstruction of cloud,identification of phenology,demand for high computing infrastructure and the complexity of statistical methods.In this research,we created a novel approach by combining four methods.First,we implemented the cloud restoration algorithm called gapfill to restore missed Normalized Difference Vegetation Index(NDVI)values derived from Sentinel-2 sensor(S2)due to cloud obstruction.Second,we created square tiles as a solution for high computing infrastructure demand due to the use of high-resolution sensor.Third,we implemented gapfill following critical crop phenology stage.Fourth,observations from restored images combined with original(from cloud-free images)values and applied for winter wheat prediction.We applied seven base machine learning as well as two groups of super learning ensembles.The study successfully applied gapfill on high-resolution image to get good quality estimates for cloudy pixels.Consequently,yield prediction accuracy increased due to the incorporation of restored values in the regression process.Base models such as Generalized Linear Regression(GLM)and Random Forest(RF)showed improved capacity compared to other base and ensemble models.The two models revealed RMSE of 0.001 t/ha and 0.136 t/ha on the holdout group.The twomodels also revealed consistent and better performance using scatter plot analysis across three datasets.The approach developed is useful to predict wheat yield at field scale,which is a rarely available but vital in many developmental projects,using optical sensors.

Quantitative design of yield components to simulate yield formation for maize in China

Maize(Zea mays L.) stands prominently as one of the major cereal crops in China as well as in the rest of the world.Therefore,predicting the growth and yield of maize for large areas through yield components under high-yielding environments will help in understanding the process of yield formation and yield potential under different environmental conditions.This accurate early assessment of yield requires accuracy in the formation process of yield components as well.In order to formulate the quantitative design for high yields of maize in China,yield performance parameters of quantitative design for high grain yields were evaluated in this study,by utilizing the yield performance equation with normalization of planting density.Planting density was evaluated by parameters including the maximum leaf area index and the maximum leaf area per plant.Results showed that the variation of the maximum leaf area per plant with varying plant density conformed to the Reciprocal Model,which proved to have excellent prediction with root mean square error(RMSE) value of 5.95%.Yield model estimation depicted that the best optimal maximum leaf area per plant was 0.63 times the potential maximum leaf area per plant of hybrids.Yield performance parameters for different yield levels were quantitatively designed based on the yield performance equation.Through validation of the yield performance model by simulating high yields of spring maize in the Inner Mongolia Autonomous Region and Jilin Province,China,and summer maize in Shandong Province,the yield performance equation showed excellent prediction with the satisfactory mean RMSE value(7.72%) of all the parameters.The present study provides theoretical support for the formulation of quantitative design for sustainable high yield of maize in China,through consideration of planting density normalization in the yield prediction process,providing there is no water and nutrient limitation.

A reliable method for predicting bioethanol yield of different varieties of sweet potato by dry matter content

In this study,we analyzed the potential of using dry matter content for determining ethanol yield of sweet potatoes as one of the raw materials for bioethanol production.We tested dry matter content,total starch content,crude protein content,glucose content,fructose content,sucrose content and fermentation indicators of 29 sweet potato varieties in Henan province.Correlation analysis between main component contents of sweet potato and the fermentation indicators were carried on.The results showed that there was strong linear correlation between dry matter content and bioethanol yield(R^2=0.935).In order to prove the conclusion,we also tested dry matter content and ethanol yield of another24 sweet potato varieties.Based on the dry matter content and linear correlations,we predicted the ethanol yields.We performed correlation analysis between the predicted values and the measured values of bioethanol yield of the 24 sweet potato varieties,and found highly significant positive correlation between the predicted values and the measured values.These results confirmed the reliability of using dry matter content for bioethanol production prediction for sweet potatoes.

Grain Yield Predict Based on GRA-AdaBoost-SVR Model

Grain yield security is a basic national policy of China,and changes in grain yield are influenced by a variety of factors,which often have a complex,non-linear relationship with each other.Therefore,this paper proposes a Grey Relational Analysis-Adaptive Boosting-Support Vector Regression(GRA-AdaBoost-SVR)model,which can ensure the prediction accuracy of the model under small sample,improve the generalization ability,and enhance the prediction accuracy.SVR allows mapping to high-dimensional spaces using kernel functions,good for solving nonlinear problems.Grain yield datasets generally have small sample sizes and many features,making SVR a promising application for grain yield datasets.However,the SVR algorithm’s own problems with the selection of parameters and kernel functions make the model less generalizable.Therefore,the Adaptive Boosting(AdaBoost)algorithm can be used.Using the SVR algorithm as a training method for base learners in the AdaBoost algorithm.Effectively address the generalization capability problem in SVR algorithms.In addition,to address the problem of sensitivity to anomalous samples in the AdaBoost algorithm,the GRA method is used to extract influence factors with higher correlation and reduce the number of anomalous samples.Finally,applying the GRA-AdaBoost-SVR model to grain yield forecasting in China.Experiments were conducted to verify the correctness of the model and to compare the effectiveness of several traditional models applied to the grain yield data.The results show that the GRA-AdaBoost-SVR algorithm improves the prediction accuracy,the model is smoother,and confirms that the model possesses better prediction performance and better generalization ability.

A METROD PREDICTING RESPONSE OF SEDIMENT YIELD TO POSSIBIE CHANGE OF PRECIPITATION DUE TO GLOBAL GREENHOUSE WARMING:AN EXAMPIE FROM NORTH FRINGE OF THE LOESS PLATEAU, CHINA

Starting from the supposition of time-space substitution, the Langbein-Schumm's Law was applied to deal with response of fluvial erosion System to the changes in mean annual Precipitation induced by global green-house warming. As a result, a simple method was put forward to predict change in sediment yield, with Ningxia Hui Autonomous Region in the northern fringe of the Loess Plateau of China as an example. Results show that, even the change in mean annual precipitation is the same, the direction and magnitude of the resultant chang in sediment yteld would be quite different in fferent physico-geographical zones. When mean annual precipitation is increased, sediment yield in arid or semi-arid areas with a mean anntal Peripitation of less than 400 mm will be increased, while sediment yield in sub-humid or humid areas with a mean annual precipitation of more than 400 mm will be decreased.Additionally, the complex response of fluvial erosion system in time series due to the lag of change in vegetation behind the changn in precipitation has also been qualitatively discussed in this paper.

Prediction of Multicomponent Reaction Yields Using Machine Learning

Prediction of reaction yields using machine learning(ML)can help chemists select high-yielding reactions and provide prior experience before wet-lab experimenting to improve efficiency.However,the exploration of a multicomponent organic reaction features many complex variables and limited number of experimental data,which are challenging for the application of ML.Herein,we perform yield prediction for the synthesis of 2-oxazolidones via Cu-catalyzed radical-type oxy-alkylation of allylamines and herteroaryl-methylamines with CO_(2),which is a three-component reaction.Using physicochemical descriptors as features to launch ML modelling,we find that XGBoost shows significantly improved performance over linear models and these features are effective for the yield prediction.Moreover,out-of-sample prediction indicates the application potential of the model.This study demonstrates great potential of regression-modelling-based ML in organic synthesis even with complex factors and a general small size of reaction data,which are generated from the classical research pattern of method for the inquiry of multicomponent reactions.

An adaptive Mealy machine model for monitoring crop status

Variation in phenological stage is the major nonlinearity in monitoring, modeling and various estimations of agricultural systems. Indices are used as a common means of evaluating agricultural monitoring data from remote sensing and terrestrial observation systems, and many of these indices have linear characteristics. The analysis of and relationships between indices are dependent on the type of plant, but they are also highly variable with respect to its phenologicat stage. For this reason, variations in the phenologica! stage affect the performance of spatiotemporal crop status monitoring. We hereby propose an adaptive event-triggered model for monitoring crop status based on remote sensing data and terrestrial observations. In the proposed model, the estimation of phenological stage is a part of predicting crop status, and spatially distributed remote sensing parameters and temporal terrestrial monitoring data are used together as inputs in a state space system model. The temporal data are segmented with respect to the phenological stage-oriented timing of the spatial data, so instead of a generalized discrete state space model, we used logical states combined with analog inputs and adaptive trigger functions, as in the case of a Mealy machine model. This provides the necessary nonlinearity for the state transi- tions. The results showed that observation parameters have considerably greater significance in crop status monitoring with respect to conventional agricultural data fusion techniques.

Yield performance estimation of corn hybrids using machine learning algorithms

Estimation of yield performance for crop products is a topic of interest in agriculture.In breeding programs,we cannot test all possible hybrids created by crossing two parents(inbred and tester)since it would be too time consuming and costly.In this paper,we exploit different machine learning algorithms including decision tree,gradient boosting machine,random forest,adaptive boosting,XGBoost and neural network to predict the yield of corn hybrids using data provided in the 2020 Syngenta Crop Challenge.The participants were asked to predict the yield of missing hybrids which were not tested before.Our results show that the prediction obtained by XGBoost is more accurate than other models with a root mean square error equal to 0.0524.Therefore,we use XGBoost model to estimate the yield performance for untested combinations of inbreds and testers.Using this approach,we identify hybrids with high predicted yield that can be bred to increase corn production.

An improved shape shifting method of critical area extraction

As die size and complexity increase, accurate and efficient extraction of the critical area is essential for yield prediction. Aiming at eliminating the potential integration errors of the traditional shape shifting method, an improved shape shifting method is proposed for Manhattan layouts. By mathematical analyses of the relevance of critical areas to defect sizes, the critical area for all defect sizes is modeled as a piecewise quadratic polynomial function of defect size, which can be obtained by extracting critical area for some certain defect sizes. Because the improved method calculates critical areas for all defect sizes instead of several discrete values with traditional shape shifting method, it eliminates the integration error of the average critical area. Experiments on industrial layouts show that the improved shape shifting method can improve the accuracy of the average critical area calculation by 24.3% or reduce about 59.7% computational expense compared with the traditional method.

Reducing deep learning network structure through variable reduction methods in crop modeling

Crop models are widely used to predict plant growth,water input requirements,and yield.However,existing models are very complex and require hundreds of variables to perform accurately.Due to these shortcomings,large-scale applications of crop models are limited.In order to address these limitations,reliable crop models were developed using a deep neural network(DNN)–a new approach for predicting crop yields.In addition,the number of required input variables was reduced using three common variable selection techniques:namely Bayesian variable selection,Spearman's rank correlation,and Principal Component Analysis Feature Extraction.The reduced-variableDNN modelswere capable of estimating future crop yields for 10,000,000 differentweather and irrigation scenarios while maintaining comparable accuracy levels to the original model that used all input variables.To establish clear superiority of the methodology,the results were also compared with a very recent feature selection algorithm called min-redundancy max-relevance(mRMR).The results of this study showed that the Bayesian variable selection was the best method for achieving the aforementioned goals.Specifically,the final Bayesian-based DNN model with a structure of 10 neurons in 5 layers performed very similarly(78.6%accuracy)to the original DNN cropmodel with 400 neurons in 10 layers,even though the size of the neural network was reduced by 80-fold.This effort can help promote sustainable agricultural intensifications through the large-scale application of crop models.