Rainfall prediction using stacked deep learning networks

Deep learning is a recently developed feature representation technique for data with complicated structures, which has great potential for soft sensing of industrial processes. However, most deep networks mainly focus on hierarchical feature learning for the raw observed input data. For soft sensor applications, it is important to reduce irrelevant information and extract quality-relevant features from the raw input data for quality prediction. To deal with this problem, a novel deep learning network is proposed for quality-relevant feature representation in this article, which is based on stacked quality-driven autoencoder (SQAE). First, a quality-driven autoencoder (QAE) is designed by exploiting the quality data to guide feature extraction with the constraint that the potential features should largely reconstruct the input layer data and the quality data at the output layer. In this way, quality-relevant features can be captured by QAE. Then, by stacking multiple QAEs to construct the deep SQAE network, SQAE can gradually reduce irrelevant features and learn hierarchical quality-relevant features. Finally, the high-level quality-relevant features can be directly applied for soft sensing of the quality variables. The effectiveness and flexibility of the proposed deep learning model are validated on an industrial debutanizer column process.

India is an agricultural region and the economy of the country depends upon agriculture. Change in climatic parameters (like rainfall, soil, etc) directly affect the growth of crops. This parameter has an unswerving effect on the quantity of food production. Information extraction from the agricultural domain through rainfall prediction has been one of the most challenging issues around the world in recent years because of climatic changes. To evaluate the feasibility of rain by employing some data analytics and machine learning techniques are developed. This paper proposes an enhanced deep learning-based approach known as Deep Regression Network (DRN). The proposed DRN is a 6-layer deep neural network. The proposed algorithm trains and tests on the agricultural corpus, collected from Dehradun (India) region. The experimental outcomes state that the proposed DRN method attained a prediction accuracy approx 86.56%. The comparative analysis shows that the proposed method outperformed existing methods like Ensemble Neural Network, Naïve Bayes, KNN, and Weighted Self-Organizing Map.

Haze caused by forest and land fires is a serious problem in South Sumatra Province. One mitigation effort that can be made is to improve the accuracy of rainfall predictions, because rain plays an important role in reducing the potential for fires. This study implements machine learning methods, namely XGBoost and ConvLSTM, to predict spatiotemporal rainfall in areas prone to haze. The results show that ConvLSTM is capable of providing better predictions than the baseline, especially during periods of haze, by considering missing data imputation and masking techniques for disrupted satellite conditions. Increasingly apparent climate change in tropical regions has had a significant impact on rainfall patterns, particularly in South Sumatra, which is one of Indonesia's main agricultural and plantation centers. High rainfall variability can lead to the risk of flooding and drought, as well as disrupting productivity in the education, health, and economic sectors. Therefore, a more accurate rainfall prediction approach is needed to support climate adaptation planning and disaster risk mitigation. This study aims to compare the performance of three approaches to daily rainfall prediction, namely the ConvLSTM-based method, XGBoost, and Persistence, using daily observation data from BMKG for the South Sumatra region for the period 1981–2020. The input variables include average air temperature (Tavg), humidity, sunshine duration, and wind speed, while rainfall is used as the prediction target. The analysis was conducted through a time series approach, statistical distribution, and model performance evaluation using the quantitative metrics Root Mean Square Error (RMSE) and Critical Success Index (CSI). The results show that the ConvLSTM model produced the highest accuracy with an average RMSE of 10 mm/day and a CSI of 0.53, which is better than XGBoost (RMSE 12 mm/day; CSI 0.48) and the persistence method (RMSE 15 mm/day; CSI 0.40). Distribution analysis indicates that light to moderate rainfall occurs more frequently, while extreme rainfall occurs sporadically. The correlation heatmap shows that rainfall has a moderate positive relationship with humidity and a negative relationship with solar radiation, while average temperature and wind play a smaller role. The main contribution of this study is to provide empirical evidence that spatiotemporal deep learning methods such as ConvLSTM are superior in modeling the complexity of tropical rainfall dynamics compared to classical machine learning approaches and simple models. These findings can serve as a basis for the development of early warning systems and interactive climate dashboards at the regional level, while enriching the literature on rainfall prediction in tropical regions using an integrative approach.

Prediction of rainfall is one of the major concerns in the domain of meteorology. Several techniques have been formerly proposed to predict rainfall based on statistical analysis, machine learning and deep learning techniques. Prediction of time series data in meteorology can assist in decision-making processes carried out by organizations responsible for the prevention of disasters. This paper presents Intensified Long Short-Term Memory (Intensified LSTM) based Recurrent Neural Network (RNN) to predict rainfall. The neural network is trained and tested using a standard dataset of rainfall. The trained network will produce predicted attribute of rainfall. The parameters considered for the evaluation of the performance and the efficiency of the proposed rainfall prediction model are Root Mean Square Error (RMSE), accuracy, number of epochs, loss, and learning rate of the network. The results obtained are compared with Holt–Winters, Extreme Learning Machine (ELM), Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network and Long Short-Term Memory models in order to exemplify the improvement in the ability to predict rainfall.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Accurate rainfall forecasting is crucial in activities such as agricultural planning, water resource management, and flood preparedness, so failure to accurately forecast rainfall might undermine these activities. This study aimed to improve the accuracy of daily rainfall prediction in Hai district, Kilimanjaro region, Tanzania, a region characterised by a bimodal rainfall pattern, by comparing rainfall prediction accuracies of Traditional Machine Learning (TML) and Deep Learning (DL) models. The 25-year daily rainfall dataset for Hai district was first pre-processed by cleaning, normalisation, and splitting into training (first 60%), validation (next 20%), and test (last 20%) sets. TML models (K-Nearest Neighbours (KNN) through its variant KNN Regressor and Support Vector Machine (SVM) through its variant Support Vector Regressor (SVR)) were developed, trained, and their performances compared with developed and trained DL models (Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU)). Each model’s test performance was evaluated using the Root Mean Squared Error (RMSE) metric. The findings revealed that the DL models, LSTM and GRU, achieved test RMSE scores of 6.35 mm and 6.49 mm, respectively, while the TML models, KNN and SVM, achieved test RMSE scores of 6.61 mm and 10.42 mm, respectively. The study demonstrated that DL models are more effective for accurate rainfall forecasting than TML models in regions with complex rainfall patterns. The insights gained will guide the development of more reliable, location-specific weather prediction systems, ultimately supporting informed decision-making in agriculture, environmental management, and flood risk reduction in Tanzania and other regions facing similar climatic challenges

Evolutionary systems such as Learning Classifier Systems (LCS) are able to learn reliably in irregular domains, while Artificial Neural Networks (ANNs) are very successful on problems with an appropriate gradient. This study introduces a novel method for discovering coarse structure, using a technique related to LCS, in combination with gradient descent. The structure used is a deep feature network, with a number of properties of a higher level of abstraction than existing ANNs, for example the network is constructed based on co-occurrence relationships, and maintained as a dynamic population of features. The feature creation technique can be considered a coarse or rapid initialization technique, that constructs a network before subsequent fine-tuning using gradient descent. The process is comparable with, but distinct from, layer-wise pretraining methods that construct and initialize a deep network prior to fine-tuning. The approach we introduce is a general learning technique, with assumptions of the dimensionality of input, and the described method uses convolved features. Results of classification of MNIST images show an average error rate of 0.79% without pre-processing or pretraining, comparable to the benchmark result provided by Restricted Boltzmann Machines of 0.95%, and 0.79% using dropout, however based on a convolutional topology, and as such our system is less general than RBM techniques, but more general than existing convolutional systems because it does not require the same domain assumptions and pre-defined topology. Use of a randomly initialized network provides a much poorer result (1.25%) indicating the coarse learning process plays a significant role. Classification of NORB images is examined, with results comparable to SVM approaches. Development of higher level relationships between features using this approach offers a distinct method of learning using a deep network of features, that can be used in combination with existing techniques.

Raman spectroscopy has attracted much attention due to its wide applications in drug detection and many other fields. However, Raman spectra often contain background noise, which poses significant challenges for subsequent analysis and processing. Although various methods for removing background noise have been proposed and have improved analysis accuracy to some extent, these mathematical model-based methods often rely on parameter adjustments based on spectral data to achieve the desired de-noising effect. The introduction of deep learning technology has provided new ideas to solve this problem, breaking through the limitations of traditional methods in parameter dependency. Different deep learning structures exhibit unique advantages when processing different types of data. In this study, we propose a static dropout triangular deep convolutional network (SD-TDCN). This deep learning network can maintain superior performance while significantly reducing the size of model parameters by statically discarding some convolutional blocks in the deep learning network. In addition, this deep learning network also lays an experimental foundation for the subsequent development of deep learning structures with adaptive dropout mechanisms.

Deep learning neural network approach to thermal-wave imaging of damage in solids with application to diffusivity measurements of a green (unsintered) metal powder compact slab

BackgroundTo determine if mammographic features from deep learning networks can be applied in breast cancer to identify groups at interval invasive cancer risk due to masking beyond using traditional breast density measures.MethodsFull-field digital screening mammograms acquired in our clinics between 2006 and 2015 were reviewed. Transfer learning of a deep learning network with weights initialized from ImageNet was performed to classify mammograms that were followed by an invasive interval or screen-detected cancer within 12 months of the mammogram. Hyperparameter optimization was performed and the network was visualized through saliency maps. Prediction loss and accuracy were calculated using this deep learning network. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were generated with the outcome of interval cancer using the deep learning network and compared to predictions from conditional logistic regression with errors quantified through contingency tables.ResultsPre-cancer mammograms of 182 interval and 173 screen-detected cancers were split into training/test cases at an 80/20 ratio. Using Breast Imaging-Reporting and Data System (BI-RADS) density alone, the ability to correctly classify interval cancers was moderate (AUC = 0.65). The optimized deep learning model achieved an AUC of 0.82. Contingency table analysis showed the network was correctly classifying 75.2% of the mammograms and that incorrect classifications were slightly more common for the interval cancer mammograms. Saliency maps of each cancer case found that local information could highly drive classification of cases more than global image information.ConclusionsPre-cancerous mammograms contain imaging information beyond breast density that can be identified with deep learning networks to predict the probability of breast cancer detection.

Detecting subtle signals from small earthquakes triggered by transient stresses from the surface waves of large magnitude earthquakes can contribute to a more general understanding of how earthquakes nucleate and interact with each other. However, searching for signals from such small earthquakes in thousands of seismograms is overwhelming, and discriminating them from a miscellany of noise is challenging. Here, we explore how we can automate the detection of such dynamically triggered earthquakes using a simple, diagnostic signal-to-noise ratio (SNR) threshold as well as a convolutional deep metric learning network. Our analysis shows that the deep learning network was more reliable at detecting small earthquakes than the SNR method.

This paper addresses the problem of rapid, precise, and efficient identification and diagnosis of grape leaf diseases by proposing the Deep-Broad Learning Network Model (ABLSS), which combines a Broad Learning network model with deep learning techniques. The model is optimized using the Adam algorithm based on BLS, and incorporates the LTM mechanism, which significantly enhances learning efficiency, stability, and recognition accuracy. Additionally, by integrating deep learning network optimization techniques, a SENet attention mechanism is added between the mapping and enhancement layers of BLS. Furthermore, based on the U-Net segmentation model, the method integrates dilated spatial pyramid pooling and feature pyramid networks. Dilated convolutions with varying dilation rates are used to capture multi-scale contextual information, which providing rich semantic information and high-resolution details during the decoding process. This improves the ABLSS model’s ability to identify small disease spots. Experimental results show that the ABLSS model achieves the highest recognition accuracy for three types of diseases with similar features on grape leaves, with an average accuracy improvement of 7.69% over BLS and 4.48% over deep learning networks. The MIOU of the segmentation model reaches 86.61%, which is a 6.48% improvement over the original U-Net model, and the MPA is 90.23%, a 8.09% improvement over the original U-Net. These results demonstrate that the proposed method significantly improves the algorithm’s recognition accuracy for small and irregular complex images. The ABLSS model recognizes images 0.375 seconds faster than the deep learning network, achieving a 72.12% speed improvement, thereby significantly enhancing the recognition efficiency of fine features. The ABLSS model combines the high recognition accuracy of deep learning with the fast processing speed of Broad Learning, while overcoming the limitations of BLS in recognizing complex images. This study provides valuable support for the development of smart orchard technologies and the optimization of learning network models.

The outbreak of COVID-19 makes it danger going out dining. Building waiterless restaurants becomes meaningful and urgent. Because automate and accurate recognition of dishes is indispensable for ordering and charging self-served food, this study investigates the feasibility of a prototype system that uses deep networks for recognizing Chinese dishes in a self-serving restaurant. Specifically, ≈ 17,000 images and 45,000 instances of 28 categories of dishes are collected using a fixed micro-camera equipment, and 5 deep learning networks are explored for dish recognition. Experimental results on the prototype system reveal that 3 transferred deep learning networks achieve high performance, and the accuracy, mean average precision and recall are larger than 97.0%. Real-time, accurate dish recognition in an automate fashion is highly related to a great customer experience, and the real-life evaluation in this study suggests that transferred deep networks are promising to fulfill this task.

Given the scarcity of annotated datasets, learning the context-dependency of anomalous events as well as mitigating false alarms represent challenges in the task of anomalous activity detection. We propose a framework, Deep-network with Multiple Ranking Measures (DMRMs), which addresses context-dependency using a joint learning technique for motion and appearance features. In DMRMs, the spatial-time-dependent features are extracted from a video using a 3D residual network (ResNet), and deep motion features are extracted by integrating the motion flow maps’ information with the 3D ResNet. Afterward, the extracted features are fused for joint learning. This data fusion is then passed through a deep neural network for deep multiple instance learning (DMIL) to learn the context-dependency in a weakly-supervised manner using the proposed multiple ranking measures (MRMs). These MRMs consider multiple measures of false alarms, and the network is trained with both normal and anomalous events, thus lowering the false alarm rate. Meanwhile, in the inference phase, the network predicts each frame’s abnormality score along with the localization of moving objects using motion flow maps. A higher abnormality score indicates the presence of an anomalous event. Experimental results on two recent and challenging datasets demonstrate that our proposed framework improves the area under the curve (AUC) score by 6.5% compared to the state-of-the-art method on the UCF-Crime dataset and shows AUC of 68.5% on the ShanghaiTech dataset.

Rainfall prediction is a significant and demanding task in today's world. Due to the nonlinearity and complication, rainfall and climate require advanced computer modeling and simulation to predict accurately. This paper comes up with a comprehensive survey and a fair comparison of several types of neural network architectures for rainfall prediction and mentions the challenges of using traditional and advanced methods in doing this task. Finally, the paper discusses the utility of deep learning methods for rainfall forecasting.