Early Forecasting of Rice Blast Disease Using Long Short-Term Memory Recurrent Neural Networks

UAV rice panicle blast detection based on enhanced feature representation and optimized attention mechanism

BACKGROUND

Rice blast is one of the most destructive diseases in rice cultivation, significantly threatening global food security. Timely and precise detection of rice panicle blast is crucial for effective disease management and prevention of crop losses. This study introduces ConvGAM, a novel semantic segmentation model leveraging the ConvNeXt-Large backbone network and the Global Attention Mechanism (GAM). This design aims to enhance feature extraction and focus on critical image regions, addressing the challenges of detecting small and complex disease patterns in UAV-captured imagery. Furthermore, the model incorporates advanced loss functions to handle data imbalances effectively, supporting accurate classification across diverse disease severities.

RESULTS

The ConvGAM model, leveraging the ConvNeXt-Large backbone network and the Global Attention Mechanism (GAM), achieves outstanding performance in feature extraction, crucial for detecting small and complex disease patterns. Quantitative evaluation demonstrates that the model achieves an overall accuracy of 91.4%, a mean IoU of 79%, and an F1 score of 82% on the test set. The incorporation of Focal Tversky Loss further enhances the model's ability to handle imbalanced datasets, improving detection accuracy for rare and severe disease categories. Correlation coefficient analysis across disease severity levels indicates high consistency between predictions and ground truth, with values ranging from 0.962 to 0.993. These results confirm the model's reliability and robustness, highlighting its effectiveness in rice panicle blast detection under challenging conditions.

CONCLUSION

The ConvGAM model demonstrates strong qualitative advantages in detecting rice panicle blast disease. By integrating advanced feature extraction with the ConvNeXt-Large backbone and GAM, the model achieves precise detection and classification across varying disease severities. The use of Focal Tversky Loss ensures robustness against dataset imbalances, enabling accurate identification of rare disease categories. Despite these strengths, future efforts should focus on improving classification accuracy and adapting the model to diverse environmental conditions. Additionally, optimizing model parameters and exploring advanced data augmentation techniques could further enhance its detection capabilities and expand its applicability to broader agricultural scenarios.

An Improved Long Short-Term Memory Algorithm for Cardiovascular Disease Prediction

Cardiovascular diseases, prevalent as leading health concerns, demand early diagnosis for effective risk prevention. Despite numerous diagnostic models, challenges persist in network configuration and performance degradation, impacting model accuracy. In response, this paper introduces the Optimally Configured and Improved Long Short-Term Memory (OCI-LSTM) model as a robust solution. Leveraging the Salp Swarm Algorithm, irrelevant features are systematically eliminated, and the Genetic Algorithm is employed to optimize the LSTM's network configuration. Validation metrics, including the accuracy, sensitivity, specificity, and F1 score, affirm the model's efficacy. Comparative analysis with a Deep Neural Network and Deep Belief Network establishes the OCI-LSTM's superiority, showcasing a notable accuracy increase of 97.11%. These advancements position the OCI-LSTM as a promising model for accurate and efficient early diagnosis of cardiovascular diseases. Future research could explore real-world implementation and further refinement for seamless integration into clinical practice.

Early Detection of Rice Blast Using a Semi-Supervised Contrastive Unpaired Translation Iterative Network Based on UAV Images

Rice blast has caused major production losses in rice, and thus the early detection of rice blast plays a crucial role in global food security. In this study, a semi-supervised contrastive unpaired translation iterative network is specifically designed based on unmanned aerial vehicle (UAV) images for rice blast detection. It incorporates multiple critic contrastive unpaired translation networks to generate fake images with different disease levels through an iterative process of data augmentation. These generated fake images, along with real images, are then used to establish a detection network called RiceBlastYolo. Notably, the RiceBlastYolo model integrates an improved fpn and a general soft labeling approach. The results show that the detection precision of RiceBlastYolo is 99.51% under intersection over union (IOU0.5) conditions and the average precision is 98.75% under IOU0.5-0.9 conditions. The precision and recall rates are respectively 98.23% and 99.99%, which are higher than those of common detection models (YOLO, YOLACT, YOLACT++, Mask R-CNN, and Faster R-CNN). Additionally, external data also verified the ability of the model. The findings demonstrate that our proposed model can accurately identify rice blast under field-scale conditions.

Application of image processing and transfer learning for the detection of rust disease

Plant diseases introduce significant yield and quality losses to the food production industry, worldwide. Early identification of an epidemic could lead to more effective management of the disease and potentially reduce yield loss and limit excessive input costs. Image processing and deep learning techniques have shown promising results in distinguishing healthy and infected plants at early stages. In this paper, the potential of four convolutional neural network models, including Xception, Residual Networks (ResNet)50, EfficientNetB4, and MobileNet, in the detection of rust disease on three commercially important field crops was evaluated. A dataset of 857 positive and 907 negative samples captured in the field and greenhouse environments were used. Training and testing of the algorithms were conducted using 70% and 30% of the data, respectively where the performance of different optimizers and learning rates were tested. Results indicated that EfficientNetB4 model was the most accurate model (average accuracy = 94.29%) in the disease detection followed by ResNet50 (average accuracy = 93.52%). Adaptive moment estimation (Adam) optimizer and learning rate of 0.001 outperformed all other corresponding hyperparameters. The findings from this study provide insights into the development of tools and gadgets useful in the automated detection of rust disease required for precision spraying.

Development of Two Early Forecasting Models for Predicting Incidence of Rice Panicle Blast in China

Early forecasting of rice panicle blast is critical to the management of rice blast. To develop early forecasting models for rice panicle blast, the relationship between the seasonal maximum incidence of rice panicle blast (PBx) and the PBx in the preceding crop, weather conditions, location, and acreage of susceptible varieties was analyzed. Results revealed that PBx in the preceding crop, acreage of the susceptible varieties in class (SVC), altitude, weather conditions 120 to 180 days before the PBx date (dbPBx) and 30 to 90 dbPBx were significantly correlated with the PBx. Subsequently, a logistic model and a two-step hurdle model were developed to predict rice panicle blast. The logistic model was developed to predict whether the PBx was 0 or not based on the preceding PBx, altitude, acreage of susceptible varieties, the longest stretch of days with soil temperatures between 16 and 24°C for the period 120 to 150 dbPBx, and the longest stretch of rainy days in the period 120 to 180 dbPBx. The hurdle model predicted if the PBx was greater than 0 at the first step, and if the prediction was greater than 0, then a regression model was developed for predicting PBx based on the preceding PBx, SVC, altitude, and weather data 180 to 30 dbPBx. Validation with the test datasets showed that the logistic model could correctly predict whether PBx was 0 at a mean test accuracy of 78.39% and that the absolute prediction error of PBx by the two-step hurdle model was smaller than 6.16% for 90% of the records. The model developed in this study will be helpful in management decisions for rice growers and policy makers and offer a useful basis for further studies on the epidemiology and forecasting of rice panicle blast.

Detection of Rice Fungal Spores Based on Micro- Hyperspectral and Microfluidic Techniques

As rice is one of the world's most important food crops, protecting it from fungal diseases is very important for agricultural production. At present, it is difficult to diagnose rice fungal diseases at an early stage using relevant technologies, and there are a lack of rapid detection methods. This study proposes a microfluidic chip-based method combined with microscopic hyperspectral detection of rice fungal disease spores. First, a microfluidic chip with a dual inlet and three-stage structure was designed to separate and enrich Magnaporthe grisea spores and Ustilaginoidea virens spores in air. Then, the microscopic hyperspectral instrument was used to collect the hyperspectral data of the fungal disease spores in the enrichment area, and the competitive adaptive reweighting algorithm (CARS) was used to screen the characteristic bands of the spectral data collected from the spores of the two fungal diseases. Finally, the support vector machine (SVM) and convolutional neural network (CNN) were used to build the full-band classification model and the CARS filtered characteristic wavelength classification model, respectively. The results showed that the actual enrichment efficiency of the microfluidic chip designed in this study on Magnaporthe grisea spores and Ustilaginoidea virens spores was 82.67% and 80.70%, respectively. In the established model, the CARS-CNN classification model is the best for the classification of Magnaporthe grisea spores and Ustilaginoidea virens spores, and its F1-core index can reach 0.960 and 0.949, respectively. This study can effectively isolate and enrich Magnaporthe grisea spores and Ustilaginoidea virens spores, providing new methods and ideas for early detection of rice fungal disease spores.

Outbreak of Rice Panicle Blast in Jeonbuk Province of Korea in 2021

Rice panicle blast is one of the most serious diseases threatening stable rice production by causing severe damage to rice yields and quality. The disease is easy to occur under low air temperature and frequent heavy rainfall during the heading season of rice. In 2021, a rice panicle blast severely occurred in the Jeonbuk province of Korea. The incidence area of panicle blast accounted for 27.7% of the rice cultivation area of Jeonbuk province in 2021, which was 13.7-times higher than in 2019 and 2.6-times higher than in 2020. This study evaluated the incidence areas of rice panicle blast in each region of Jeonbuk province in 2021. The weather conditions during the heading season of rice, mainly cultivated rice cultivars, and the race diversity of the Jeonbuk isolates were also investigated. It will provide important information for the effective control of the rice panicle blast.

Optimizing Artificial Neural Network-Based Models to Predict Rice Blast Epidemics in Korea

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory (LSTM), with diverse input datasets, and compares their performance. The Blast_Weather_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

Time series forecasting for uni- variant data using hybrid GA-OLSTM model and performance evaluations

Time series forecasting of uni-variant rainfall data is done using a hybrid genetic algorithm integrated with optimized long-short term memory (GA-OLSTM) model. The parameters included for the valuation of the efficiency of the considered model, were mean square error (MSE), root mean square error (RMSE), cosine similarity (CS) and correlation coefficient (r). With various epochs like 5, 10, 15 and 20, the optimal window size and the number of units were observed using the GA search algorithm which was found to be (49, 9), (12, 8), (40, 8), and (36, 2) respectively. The computed MSE, RMSE, CS and r for 10 epochs were found to be 0.006, 0.078, 0.910 and 0.858 respectively for the LSTM model, whereas the same parameters were computed using the Hybrid GA-OLSTM model was 0.004, 0.063, 0.947 and 0.917 respectively. The experimental results expressed that the Hybrid GA-OLSTM model gave significantly better results comparing the LSTM model for 10 epochs has been discussed in this research article.

Outbreak of Rice Blast Disease at Yeoju of Korea in 2020

Rice blast is the most destructive disease threatening stable rice production in rice-growing areas. Cultivation of disease-resistant rice cultivars is the most effective way to control rice blast disease. However, the rice blast resistance is easy to breakdown within years by blast fungus that continually changes to adapt to new cultivars. Therefore, it is important to continuously monitor the incidence of rice blast disease and race differentiation of rice blast fungus in fields. In 2020, a severe rice blast disease occurred nationwide in Korea. We evaluated the incidence of rice blast disease in Yeoju and compared the weather conditions at the periods of rice blast disease in 2019 and 2020. We investigated the races and avirulence genes of rice blast isolates in Yeoju to identify race diversity and genetic characteristics of the isolates. This study will provide empirical support for rice blast control and the breeding of blast-resistant rice cultivars.

Forecasting Plant and Crop Disease: An Explorative Study on Current Algorithms

Every year, plant diseases cause a significant loss of valuable food crops around the world. The plant and crop disease management practice implemented in order to mitigate damages have changed considerably. Today, through the application of new information and communication technologies, it is possible to predict the onset or change in the severity of diseases using modern big data analysis techniques. In this paper, we present an analysis and classification of research studies conducted over the past decade that forecast the onset of disease at a pre-symptomatic stage (i.e., symptoms not visible to the naked eye) or at an early stage. We examine the specific approaches and methods adopted, pre-processing techniques and data used, performance metrics, and expected results, highlighting the issues encountered. The results of the study reveal that this practice is still in its infancy and that many barriers need to be overcome.

A method for hand-foot-mouth disease prediction using GeoDetector and LSTM model in Guangxi, China

Hand-foot-mouth disease (HFMD) is a common infectious disease in children and is particularly severe in Guangxi, China. Meteorological conditions are known to play a pivotal role in the HFMD. Previous studies have reported numerous models to predict the incidence of HFMD. In this study, we proposed a new method for the HFMD prediction using GeoDetector and a Long Short-Term Memory neural network (LSTM). The daily meteorological factors and HFMD records in Guangxi during 2014–2015 were adopted. First, potential risk factors for the occurrence of HFMD were identified based on the GeoDetector. Then, region-specific prediction models were developed in 14 administrative regions of Guangxi, China using an optimized three-layer LSTM model. Prediction results (the R-square ranges from 0.39 to 0.71) showed that the model proposed in this study had a good performance in HFMD predictions. This model could provide support for the prevention and control of HFMD. Moreover, this model could also be extended to the time series prediction of other infectious diseases.

Predicting rice blast disease: machine learning versus process-based models

BACKGROUND

In this study, we compared four models for predicting rice blast disease, two operational process-based models (Yoshino and Water Accounting Rice Model (WARM)) and two approaches based on machine learning algorithms (M5Rules and Recurrent Neural Networks (RNN)), the former inducing a rule-based model and the latter building a neural network. In situ telemetry is important to obtain quality in-field data for predictive models and this was a key aspect of the RICE-GUARD project on which this study is based. According to the authors, this is the first time process-based and machine learning modelling approaches for supporting plant disease management are compared.

RESULTS

Results clearly showed that the models succeeded in providing a warning of rice blast onset and presence, thus representing suitable solutions for preventive remedial actions targeting the mitigation of yield losses and the reduction of fungicide use. All methods gave significant "signals" during the "early warning" period, with a similar level of performance. M5Rules and WARM gave the maximum average normalized scores of 0.80 and 0.77, respectively, whereas Yoshino gave the best score for one site (Kalochori 2015). The best average values of r and r2 and %MAE (Mean Absolute Error) for the machine learning models were 0.70, 0.50 and 0.75, respectively and for the process-based models the corresponding values were 0.59, 0.40 and 0.82. Thus it has been found that the ML models are competitive with the process-based models. This result has relevant implications for the operational use of the models, since most of the available studies are limited to the analysis of the relationship between the model outputs and the incidence of rice blast. Results also showed that machine learning methods approximated the performances of two process-based models used for years in operational contexts.

CONCLUSIONS

Process-based and data-driven models can be used to provide early warnings to anticipate rice blast and detect its presence, thus supporting fungicide applications. Data-driven models derived from machine learning methods are a viable alternative to process-based approaches and - in cases when training datasets are available - offer a potentially greater adaptability to new contexts.

Portable Rice Disease Spores Capture and Detection Method Using Diffraction Fingerprints on Microfluidic Chip

Crop diseases cause great harm to food security, 90% of these are caused by fungal spores. This paper proposes a crop diseases spore detection method, based on the lensfree diffraction fingerprint and microfluidic chip. The spore diffraction images are obtained by a designed large field of view lensless diffraction detection platform which contains the spore enrichment microfluidic chip and lensless imaging module. By using the microfluidic chip to enrich and isolate spores in advance, the required particles can be captured in the chip enrichment area, and other impurities can be filtered to reduce the interference of impurities on spore detection. The light source emits partially coherent light and irradiates the target to generate diffraction fingerprints, which can be used to distinguish spores and impurities. According to the theoretical analysis, two parameters, Peak to Center ratio (PCR) and Peak to Valley ratio (PVR), are found to quantify these spores. The correlation coefficient between the detection results of rice blast spores by the constructed device and the results of microscopic artificial identification was up to 0.99, and the average error rate of the proposed device was only 5.91%. The size of the device is only 4 cm × 4 cm × 5 cm, and the cost is less than $150, which is one thousandth of the existing equipment. Therefore, it may be widely used as an early detection method for crop disease caused by spores.

Genetic Algorithm-Optimized Long Short-Term Memory Network for Stock Market Prediction

With recent advances in computing technology, massive amounts of data and information are being constantly accumulated. Especially in the field of finance, we have great opportunities to create useful insights by analyzing that information, because the financial market produces a tremendous amount of real-time data, including transaction records. Accordingly, this study intends to develop a novel stock market prediction model using the available financial data. We adopt deep learning technique because of its excellent learning ability from the massive dataset. In this study, we propose a hybrid approach integrating long short-term memory (LSTM) network and genetic algorithm (GA). Heretofore, trial and error based on heuristics is commonly used to estimate the time window size and architectural factors of LSTM network. This research investigates the temporal property of stock market data by suggesting a systematic method to determine the time window size and topology for the LSTM network using GA. To evaluate the proposed hybrid approach, we have chosen daily Korea Stock Price Index (KOSPI) data. The experimental result demonstrates that the hybrid model of LSTM network and GA outperforms the benchmark model.