Modeling and Predicting Rice Gall Midge Populations Using Climate Data and Machine Learning Techniques in Andhra Pradesh

Brown Planthopper (BPH) (Nilaparvata lugens) is a major pest impacting rice production in India, often causing severe yield losses across diverse agro-climatic zones. This study evaluates the predictive capabilities of several statistical and machine learning models using weekly BPH incidence data collected over multiple years from five research stations in Andhra Pradesh (Nellore, Maruteru, Bapatla, Ragolu, and Nandyal). The models tested include the Negative Binomial Integer-Valued Generalized Autoregressive Conditional Heteroskedasticity (NBINGARCH) model in combination with Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Extreme Learning Machines (ELM), as well as their standalone counterparts. Hybrid models, particularly NBINGARCH-SVR and NBINGARCH-ELM, outperformed standalone models based on Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) across different locations and seasons. Some models, however, demonstrated signs of overfitting, as evident in elevated testing errors. Climatic variables—temperature, relative humidity, and rainfall—were found to significantly influence BPH dynamics. While the Box-Pierce test confirmed model adequacy in most cases, residual autocorrelation remained in a few, indicating room for further refinement. These results highlight the potential of hybrid modeling approaches for climate-informed BPH forecasting and offer actionable insights for Integrated Pest Management (IPM). Future work may enhance forecasting accuracy by incorporating additional environmental and agronomic parameters.

The Asian rice gall midge, Orseolia oryzae is a one of the major pest of rice which seriously infests the rice of several Asian countries and it causes major economic loses. The formation of silvery white hollow tube gall (silver shoot) is the major symptom of the rice gall midge infestation. Different biotypes or populations of rice gall midge were observed after the wide use of gall midge resistant rice varieties and the chemical control of the gal midge is difficult, because the larvae are safe inside the gall. In this study we have developed a DNA barcode and determined the phylogenetic status of Asian rice gall midge, O. oryzae in Cecidomyiidae family. Among the species used in this study F. acarivora is the nearest relative of O. oryzae and R. yagoi is the distant relative and the mitochondrial DNA of the O. oryzae also showed clear bias to AT and it showed close similarity mean observed AT composition of the insect mtDNA. This study also revealed that the nucleotides in the each codone position of O. oryzae have variation in the strong and less constrained position of codones with other species of Cecidomyiidae family.

Six distinct biotypes of the Asian rice gall midge, Orseolia oryzae (Wood-Mason), have been characterized so far from different parts of India and their geographical distribution has been well mapped and monitored annually through the national gall midge biotype studies. These studies have been showing minor changes in the virulence pattern of the pest population at Warangal in Andhra Pradesh state since 2000. Hence, a sample of the pest population from the site was collected during 2003 and selected subsequently in a greenhouse through 13 successive generations for virulence against diverse sources of plant resistance. This Warangal-derived population (WDP) was tested to record reactions of two sets of differential rice varieties used for biotype detection and known to carry one of the 10 known gall midge-resistance genes. The results revealed that WDP has acquired virulence against CR-MR1523, one of the biotype differential rice varieties, which derived resistance from the source Ptb21 cultivar. Since the virulence pattern noted for WDP was different from that noted for the six characterized biotypes, it is proposed to designate this new biotype, tentatively, as biotype 4M. Only three of the resistance genes, viz. Gm3, Gm4 and Gm8 confer resistance against this biotype.

The Asian rice gall midge, Orseolia oryzae, is an important pest of rice. Gm4, a major rice gall midge resistance gene in the indica rice variety Abhaya has been fine mapped within 0.3 Mb region with the flanking markers RM22551 and RM22562. Among the 70 putative candidate genes identified in the reference Nipponbare rice genome in this region, two genes coding for leucine rich repeat (LRR) proteins were shortlisted for further analysis. Polymorphisms was observed between the parents improved samba masuri (ISM) (susceptible parent) and Abhaya (resistant parent) and the recombinant inbred line (RIL)-derived near isogenic lines (pre-NILs) 482R (resistant line) and 489S (susceptible line) with one pair of the markers targeting the candidate genes. Polymorphism co-segregated with the trait in a larger mapping population consisting of 40 resistant and 40 susceptible RILs (F10 generation). A major segment of this gene (LOC_Os08g09670.1), covering one of the two exons, was cloned and sequenced from both parents as well as from the two pre-NILs 482R and 489S. Data revealed a large deletion in the Abhaya fragment as compared to that of ISM. At least five amino acid substitutions were detected, between the alleles, that are likely to influence the protein function. Expression analysis of this putative candidate gene through reverse transcription real time PCR showed more than two fold increase in its expression levels in the resistant parent Abhaya and resistant line 482R at 24 h after gall midge infestation when compared with the uninfested controls. These results suggested the LRR coding gene to be the candidate for Gm4. In addition, the current work also identified a functional marker (LRR-del) for the detection of the gene for use in marker-assisted introgression of Gm4.

Yellow Stem Borer (YSB) (Scirpophaga incertulas) is one of the most destructive pests affecting rice production in India, causing significant yield losses across different agro-climatic regions. Accurate forecasting of YSB populations is crucial for timely pest management and minimizing crop damage. This study evaluates the performance of statistical and machine learning models for predicting YSB populations using weekly pest incidence data collected from five research stations in Andhra Pradesh (Nellore, Maruteru, Bapatla, Ragolu, and Nandyal) over multiple years. The study employs Integer-Valued Generalized Autoregressive Conditional Heteroskedastic (INGARCH) models along with Artificial Neural Networks (ANN), Support Vector Regression (SVR), Extreme Learning Machines (ELM), and their hybrid counterparts (INGARCH-ANN, INGARCH-SVR, and INGARCH-ELM) to improve forecasting accuracy. Results indicate that hybrid models, particularly NBINGARCH-ELM, consistently outperformed standalone models in terms of Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) across different locations and seasons. The findings reveal that YSB populations are significantly influenced by climatic factors such as temperature, relative humidity, and rainfall, with distinct seasonal patterns. The Box-Pierce test confirmed minimal autocorrelation in residuals for most models, validating their reliability. These results highlight the potential of hybrid statistical machine learning models for pest forecasting, providing valuable insights for integrated pest management (IPM) strategies. Future research can further enhance these models by incorporating additional environmental and agronomic variables for improved precision in pest outbreak predictions.

The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.

Global solar radiation prediction by ANN integrated with European Centre for medium range weather forecast fields in solar rich cities of Queensland Australia

River stream estimation is a subject matter that needs constant research and development since it is all-important in the management of water resources, meeting the water demand, irrigation and agricultural activities, and providing distant signal in unwanted situations such as floods. Unfortunately, a universal technique has been impossible to talk about yet although many techniques have been used for estimation and modeling. This has made it necessary to develop different techniques and / or to make comparisons between techniques and to determine the most accurate method for the parameters used. In this context, in this study, the distribution graphs of the flow data fourteen stations located in the Euphrates-Tigris Basin for the years 1981-2010 were created and their conformity to the normal distribution was investigated Evaluation has been made with Adaptive Neural Fuzzy Logic System (ANFIS), Support Vector Regression (SVR) techniques and the newly introduced Gaussian Process Regression (GPR), Extreme Learning Machine (ELM) and Emotional Neural Networks (ENN) artificial intelligence techniques. Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE) and correlation coefficient (r), which are frequently used, were used to determine the model performance. In addition, it is aimed to find out which technique gives better results with rank analysis. Although all models work well, the sequence with regards to the comparison outcomes of the techniques obtained from rank analysis was observed to be ELM, GPR, ENN, SVR, ANFIS respectively. In order to better interpret the results, Taylor diagrams and time series graphics of the model outputs were created.

Purpose: This study aims to propose a hybrid model that integrates machine learning techniques with time series modeling and takes into account the Internet information represented by Google Trends to combine structural data and big data for vegetable price modeling. The hybrid model is expected to enhance the prediction performance of vegetable prices. Design/methodology/approach: Time series models commonly used for price prediction (e.g., autoregressive integrated moving average model [ARIMA], autoregressive conditional heteroscedasticity model [ARCH], and generalized ARCH model [GARCH]) and machine learning techniques usually used for vegetable price forecast (e.g., artificial neural networks [ANN] and support vector regression [SVR]) are selected to obtain prediction models in this study. Seven prediction models classified into three categories are selected for empirical comparison: (1) time series model, ANN, and SVR models fitted with only cabbage prices, (2) ANN and SVR models fitted with both cabbage prices and Google Trends, and (3) two hybrid models, integrated time series model with machine learning techniques (SVR or ANN) and fitted with both cabbage prices and Google Trends. Daily cabbage prices and its Google Trends of searching volumes are used for empirical analysis. The prediction performance of seven prediction models is compared based on the mean absolute percentage error (MAPE), mean absolute error (MAE), and the root mean squared error (RMSE). Findings: Study results show that (1) the models considering the information of Google Trends with cabbage prices perform better than those models using only cabbage prices, (2) the hybrid models presented in this paper have significantly improved the prediction performance of the time series model, and (3) the hybrid model integrated time series model with SVR algorithm has the best prediction performance. Practical implications: In practice, the hybrid model proposed in this study can be applied to vegetable price forecasting to improve prediction performance. Originality/value: Our study findings contribute to the forecasting methodology of integrated statistical modeling with machine learning techniques and using both structural data and big data for improving prediction modeling of vegetable prices.

Real-time porosity prediction using gas-while-drilling data and machine learning with reservoir associated gas: Case study for Hassi Messaoud field, Algeria

PurposeThis study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.Design/methodology/approachAutoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.FindingsThe results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.Research limitations/implicationsThe foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.Originality/valueThis is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

Aim: To determine the effect of local rice cultivars and inorganic nitrogen fertilizer on the incidence of stem borer, Scirpophaga incertulas (Walker); leaffolder, Cnephalocrocis medinalis (Guenee); and gall midge, Orseolia oryzae (Wood Mason) and on grain yield of rice.
 Study Design: A field experiment for two consecutive years was carried out in a split-plot arrangement in randomized block design with three replications.
 Place and duration of the study: Department of Entomology, Agricultural Research Station, Nellore, Andhra Pradesh, India during Kharif, 2013 and 2014.
 Methodology: The rice cultivars (NLR 20104, NLR 20106, NLR 3135 and NLR 33892) were attributed to experimental main plots and nitrogen levels (40, 80, 120, 160 and 200 kg ha-1) to the sub plots. Observations on incidence of stem borer, gall midge and leaf folder was recorded in randomly selected 10 hills per subplot in replication and percent incidence was calculated.
 Results: The pest incidence for the treatments with high N rate as 160 and 200 kg/ha was higher (31.43 & 43.86% stem borer, 9.23 & 13.59% leaffolder and 2.75 & 3.00% gall midge, respectively) than that for lower N rate i.e. 40 and 80 kg ha-1 (19.24 & 20.04% stem borer, 7.37 & 7.95% leaffolder and 1.42 & 1.93% gall midge, respectively). Different rice cultivars significantly influenced the leaffolder incidence but not the stem borer and gall midge incidence. The Highest leaffolder incidence (13.44%) was noticed in NLR 20104 cultivar which was followed by NLR 3135 cultivar with 9.64% leaffolder incidence. Gall midge and leaffolder incidence was not significantly influenced by the combined effect of rice cultivar and nitrogen levels; in contrast, interaction effect has a significant influence on stem borer incidence. Significantly lowest stem borer incidence (18.21%) was noticed with NLR 3135 rice cultivar treated with 40 N ha-1, which was statistically on par with the NLR 20106 rice cultivar treated with 40 kg N ha-1 (18.23%) and NLR 20104 rice cultivar treated with 40 kg N ha-1 (19.76%). Among the different cultivarscultivar, NLR 33892 cultivarhad produced significantly highest grain yield (5955 kg ha-1) may be for having higher physiological indices. The highest/optimum grain yield (5726 kg ha-1) produced by plots that received 120 kg N ha-1. Further increase in nitrogen level beyond 120 kg ha-1 did not significantly improve the grain yield. Optimal N rate was revealed to be 120 kg ha-1 for four rice cultivars for reducing the stem borer/leaffolder/gall midge incidence so as to minimize the cost of inputs for pest control measures and for achieving high grain yield.
 Conclusions: The incremental doses of nitrogen fertilizer significantly enhanced stem borer, leaffolder and gall midge infestation on rice, which further affects the grain yields.

Comparative analysis of machine learning models for rainfall prediction

Forecasting malaria incidence is vital for effective resource allocation during malaria elimination. In this study, we highlight robust models for forecasting incidence using climatic and malaria data from Goa, India. Multi-collinearity and Shapley Additive Explanations (SHAP) were used to identify most important predictors of malaria transmission among 15 climatic variables. Three machine-learning models (Support vector machines, Random Forest, Extreme gradient boosting), three time-series models (ARIMA, SARIMA, SARIMAX), and three hybrid models (RF-ARMA, SVM-ARMA, XGB-ARMA) were then trained and tested on data spanning from 2010 to 2019. Climatic extremes have stronger influence on malaria transmission than average values in Goa. Machine learning models exhibit lower accuracy (Root Mean Square Error (RMSE):13–37) but high precision (lower confidence intervals). Conversely, time series models, yielded more accurate results (RMSE: 5–41) albeit with less precision (wider confidence interval). To address this, we augmented machine learning models by incorporating time series variables which significantly bolstered their accuracy while retaining their inherent precision (RMSE: 0·5-15). Integrating time-series components into machine learning models harnesses the strengths of both approaches resulting in a substantial enhancement in accuracy and precision of forecasts. This technique has potential for wider use in planning malaria elimination, and routine epidemiological data analysis.

Stream temperature (Ts) is an important water quality parameter that affects ecosystem health and human water use for beneficial purposes. Accurate Ts predictions at different spatial and temporal scales can inform water management decisions that account for the effects of changing climate and extreme events. In particular, widespread predictions of Ts in unmonitored stream reaches can enable decision makers to be responsive to changes caused by unforeseen disturbances. In this study, we demonstrate the use of classical machine learning (ML) models, support vector regression and gradient boosted trees (XGBoost), for monthly Ts predictions in 78 pristine and human-impacted catchments of the Mid-Atlantic and Pacific Northwest hydrologic regions spanning different geologies, climate, and land use. The ML models were trained using long-term monitoring data from 1980–2020 for three scenarios: (1) temporal predictions at a single site, (2) temporal predictions for multiple sites within a region, and (3) spatiotemporal predictions in unmonitored basins (PUB). In the first two scenarios, the ML models predicted Ts with median root mean squared errors (RMSE) of 0.69–0.84 °C and 0.92–1.02 °C across different model types for the temporal predictions at single and multiple sites respectively. For the PUB scenario, we used a bootstrap aggregation approach using models trained with different subsets of data, for which an ensemble XGBoost implementation outperformed all other modeling configurations (median RMSE 0.62 °C).The ML models improved median monthly Ts estimates compared to baseline statistical multi-linear regression models by 15–48% depending on the site and scenario. Air temperature was found to be the primary driver of monthly Ts for all sites, with secondary influence of month of the year (seasonality) and solar radiation, while discharge was a significant predictor at only 10 sites. The predictive performance of the ML models was robust to configuration changes in model setup and inputs, but was influenced by the distance to the nearest dam with RMSE <1 °C at sites situated greater than 16 and 44 km from a dam for the temporal single site and regional scenarios, and over 1.4 km from a dam for the PUB scenario. Our results show that classical ML models with solely meteorological inputs can be used for spatial and temporal predictions of monthly Ts in pristine and managed basins with reasonable (<1 °C) accuracy for most locations.