Biometeorological and autoregressive indices for predicting olive pollen intensity

This paper reports on modelling to predict airborne olive pollen season severity, expressed as a pollen index (PI), in Córdoba province (southern Spain) several weeks prior to the pollen season start. Using a 29-year database (1982–2010), a multivariate regression model based on five indices—the index-based model—was built to enhance the efficacy of prediction models. Four of the indices used were biometeorological indices: thermal index, pre-flowering hydric index, dormancy hydric index and summer index; the fifth was an autoregressive cyclicity index based on pollen data from previous years. The extreme weather events characteristic of the Mediterranean climate were also taken into account by applying different adjustment criteria. The results obtained with this model were compared with those yielded by a traditional meteorological-based model built using multivariate regression analysis of simple meteorological-related variables. The performance of the models (confidence intervals, significance levels and standard errors) was compared, and they were also validated using the bootstrap method. The index-based model built on biometeorological and cyclicity indices was found to perform better for olive pollen forecasting purposes than the traditional meteorological-based model.     

Toxic gas dispersion prediction for point source emission using deep learning method

Abstract

Accurate and rapid toxic gas concentration prediction model plays an important role in emergency aid of sudden gas leak. However, it is difficult for existing dispersion model to achieve accuracy and efficiency requirements at the same time. Although some researchers have considered developing new forecasting models with traditional machine learning, such as back propagation (BP) neural network, support vector machine (SVM), the prediction results obtained from such models need to be improved still in terms of accuracy. Then new prediction models based on deep learning are proposed in this paper. Deep learning has obvious advantages over traditional machine learning in prediction and classification. Deep belief networks (DBNs) as well as convolution neural networks (CNNs) are used to build new dispersion models here. Both models are compared with Gaussian plume model, computation fluid dynamics (CFD) model and models based on traditional machine learning in terms of accuracy, prediction time, and computation time. The experimental results turn out that CNNs model performs better considering all evaluation indexes.     

Spatio-temporal air quality analysis and PM2.5 prediction over Hyderabad City,India using artificial intelligence techniques

Air pollution is one of the most serious environmental issues faced by humans, and it affects the quality of life in cities. PM_2.5 forecasting models can be used to create strategies for assessing and warning the public about anticipated harmful levels of air pollution. Accurate pollutant concentration measurements and forecasting are critical criteria for assessing air quality and are the foundation for making the right strategic decisions. Data-driven machine learning models for PM_2.5 forecasting have gained attention in the recent past. In this study, PM_2.5 prediction for Hyderabad city was carried out using various machine learning models viz. Multi-Linear Regression (MLR), decision tree (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and XGBoost. A deep learning model, the Long Short-Term Memory (LSTM) model, was also used in this study. The results obtained were finally compared based on error and R² value. The best model was selected based on its maximum R² value and minimal error. The model's performance was further improved using the randomized search CV hyperparameter optimization technique. Spatio-temporal air quality analysis was initially conducted, and it was found that the average winter PM_2.5 concentrations were 68% higher than the concentrations in summer. The analysis revealed that XGBoost regression was the best-performing machine learning model with an R² value of 0.82 and a Mean Absolute Error (MAE) of 7.01 μg/ m³, whereas the LSTM deep learning model performed better than XGBoost regression for PM_2.5 modeling with an R² value of 0.89 and an MAE of 5.78 μg/ m³.     

Weather factors in the short-term forecasting of daily ambulance calls

The daily ambulance demand for Hong Kong is rising, and it has been shown that weather factors (temperature and humidity) play a role in the demand for ambulance services. This study aimed at developing short-term forecasting models of daily ambulance calls using the 7-day weather forecast data as predictors. We employed the autoregressive integrated moving average (ARIMA) method to analyze over 1.3 million cases of emergency attendance in May 2006 through April 2009 and the 7-day weather forecast data for the same period. Our results showed that the ARIMA model could offer reasonably accurate forecasts of daily ambulance calls at 1–7 days ahead of time and with improved accuracy by including weather factors. Specifically, the inclusion of average temperature alone in our ARIMA model improved the predictability of the 1-day forecast when compared to that of a simple ARIMA model (8.8 % decrease in the root mean square error, RMSE?=?53 vs 58). The improvement in the 7-day forecast with average temperature as a predictor was more pronounced, with a 10 % drop in prediction error (RMSE?=?62 vs 69). These findings suggested that weather forecast data can improve the 1- to 7-day forecasts of daily ambulance demand. As weather forecast data are readily accessible from Hong Kong Observatory’s official website, there is virtually no cost to including them in the ARIMA models, which yield better prediction for forward planning and deployment of ambulance manpower.     

Forecasting vegetation indices from spatio-temporal remotely sensed data using deep learning-based approaches: A systematic literature review

Over the last few years, Deep learning (DL) approaches have been shown to outperform state-of-the-art machine learning (ML) techniques in many applications such as vegetation forecasting, sales forecast, weather conditions, crop yield prediction, landslides detection and even COVID-19 spread predictions. Several DL algorithms have been employed to facilitate vegetation forecasting research using Remotely Sensed (RS) data. Vegetation is an extremely important component of our global ecosystem and a necessary indicator of land cover dynamics and productivity. Vegetation phenology is influenced by lifecycle patterns, seasonality and weather conditions, leading to changes in their spectral reflectance. Various relevant information, such as vegetation indices (VIs), can be extracted from RS data for vegetation forecasting. Therefore, the Normalized Difference Vegetation Index (NDVI) is known as one of the most widely recognized indices for vegetation related studies. This paper reviews the related works on DL-based spatio-temporal vegetation forecasting using RS data over the period between 2015 and 2021. In this review, we present several DL-based studies and discuss DL algorithms and various sources of data that have been used in these studies. The purpose of this work is to highlight the open challenges such as spatio-temporal prediction issues, spatial and temporal non-stationarity, fusion data, hybrid approaches, deep transfer learning and large parameter requirements. We also attempt to figure out the future directions and limits of DL for vegetation forecasting.     

Modeling vegetation greenness and its climate sensitivity with deep‐learning technology

Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–vegetation models based on long short‐term memory (LSTM) network, which is a powerful deep‐learning algorithm for long‐time series modeling, to achieve accurate vegetation monitoring and investigate the complex relationship between climate and vegetation. We selected the normalized difference vegetation index (NDVI) that represents vegetation greenness as model outputs. The climate data (monthly temperature and precipitation) were used as inputs. We trained the networks with data from 1982 to 2003, and the data from 2004 to 2015 were used to validate the models. Error analysis and sensitivity analysis were performed to assess the model errors and investigate the sensitivity of global vegetation to climate change. Results show that models based on deep learning are very effective in simulating and predicting the vegetation greenness dynamics. For models training, the root mean square error (RMSE) is <0.01. Model validation also assure the accuracy of our models. Furthermore, sensitivity analysis of models revealed a spatial pattern of global vegetation to climate, which provides us a new way to investigate the climate sensitivity of vegetation. Our study suggests that it is a good way to integrate deep‐learning method to monitor the vegetation change under global change. In the future, we can explore more complex climatic and ecological systems with deep learning and coupling with certain physical process to better understand the nature.     

Year clustering analysis for modelling olive flowering phenology

It is now widely accepted that weather conditions occurring several months prior to the onset of flowering have a major influence on various aspects of olive reproductive phenology, including flowering intensity. Given the variable characteristics of the Mediterranean climate, we analyse its influence on the registered variations in olive flowering intensity in southern Spain, and relate them to previous climatic parameters using a year-clustering approach, as a first step towards an olive flowering phenology model adapted to different year categories. Phenological data from Cordoba province (Southern Spain) for a 30-year period (1982–2011) were analysed. Meteorological and phenological data were first subjected to both hierarchical and “K-means” clustering analysis, which yielded four year-categories. For this classification purpose, three different models were tested: (1) discriminant analysis; (2) decision-tree analysis; and (3) neural network analysis. Comparison of the results showed that the neural-networks model was the most effective, classifying four different year categories with clearly distinct weather features. Flowering-intensity models were constructed for each year category using the partial least squares regression method. These category-specific models proved to be more effective than general models. They are better suited to the variability of the Mediterranean climate, due to the different response of plants to the same environmental stimuli depending on the previous weather conditions in any given year. The present detailed analysis of the influence of weather patterns of different years on olive phenology will help us to understand the short-term effects of climate change on olive crop in the Mediterranean area that is highly affected by it.     

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

BackgroundIn the past few decades, several researchers have proposed highly accurate prediction models that have typically relied on climate parameters. However, climate factors can be unreliable and can lower the effectiveness of prediction when they are applied in locations where climate factors do not differ significantly. The purpose of this study was to improve a dengue surveillance system in areas with similar climate by exploiting the infection rate in the Aedes aegypti mosquito and using the support vector machine (SVM) technique for forecasting the dengue morbidity rate.ConclusionsThe infection rates of the Ae. aegypti female mosquitoes and larvae improved the morbidity rate forecasting efficiency better than the climate parameters used in classical frameworks. We demonstrated that the SVM-R-based model has high generalization performance and obtained the highest prediction performance compared to classical models as measured by the accuracy, sensitivity, specificity, and mean absolute error (MAE).     

Improving phenological forecasting models for rape stem weevil,Ceutorhynchus napi Gyll., based on long‐term multisite datasets

New threshold‐based models to predict the start of invasion by the stem‐boring pest, the rape stem weevil (Ceutorhynchus napi Gyll.) of winter oilseed rape (Brassica napus L.), were developed and compared to published models using long‐term datasets on weather and weevil phenology from experimental locations in Germany and Luxembourg. Threshold values for daily records of maximum air temperature, mean soil temperature, sunshine duration and total precipitation were adjusted to local conditions on the date of first weevil migration in spring. Mean error and the root mean squared error were used to assess model quality, where the error is defined as the number of days between predicted and observed arrival of weevils on the crop (regardless of sign). Best model results predicted first crop invasion by rape stem weevil when the thresholds of daily maximum air temperature ≥7.8°C, mean soil temperature ≥6.6°C, daily total precipitation ≤1.0 mm and sunshine duration ≥1 h were matched. This model takes into account meteorological variables likely to influence conditions at the overwintering site of the weevils in the soil, as well as variables that may limit weevil flight. Adjusted air temperature threshold values were consistently lower for Luxembourg sites than for those optimized for Germany. A simple model relating the date of first weevil invasion to accumulated daily maximum air temperature above 0°C (from 1 January) was also evaluated. This proved less suitable for forecasting crop invasion by C. napi. We suggest that phenological models using locally adjusted meteorological‐based thresholds have the potential to offer sufficiently accurate forecasts of first immigration flights by C. napi for appropriate timing of insecticide application. In addition, the developed models are suitable tools to be used in climate change impact studies.     

Application-oriented deep learning model for early warning of rice blast in Taiwan

Rice blast is one of the most devastating diseases that threatens rice production in Taiwan. A rice blast forecasting model is required to guide the precise application of fungicide. Therefore, BlastGRU-TW model based on deep learning algorithms was developed in this study. The input data comprised approximately 1000 rice blast surveys, collected from 50 fields throughout Taiwan between 2014 and 2021, and the corresponding weather data retrieved from weather observation network in Taiwan. Common and easily accessible meteorological factors, i.e. temperature, humidity, precipitation, and wind, were converted into 20 daily meteorological features which were coupled with different time intervals between 1 and 30 days before survey (DBS) to train the model. The results showed that seven meteorological features (daily maximum temperature, daily mean temperature, daily minimum temperature, daily mean humidity, daily mean WV and daily mean Wu) and the interval from −4 to −24 DBS were informative in disease prediction, thereby indicating that the proposed model could predict the risk of rice blast by using meteorological data 4–24 days before new disease symptoms appeared. The proposed BlastGRU-TW model achieved an accuracy of 87.3%. Furthermore, on adding the 3 day forecast weather data from Weather Research and Forecasting (WRF) model in the proposed model, the forecast extended to 7 days ahead of the appearance of new symptoms. Moreover, the BLASTAM model developed in Japan was implemented and validated in Taiwan to evaluate its applicability in different geographical areas. Finally, a rice blast early warning system (https://mycolab.pp.nchu.edu.tw/blast_forecast/index_en.php) equipped with an interactive web-based map is now available for real-time forecasting of the risk of rice blast in paddy field across Taiwan.     

Ketamine Effects on Memory Reconsolidation Favor a Learning Model of Delusions

Delusions are the persistent and often bizarre beliefs that characterise psychosis. Previous studies have suggested that their emergence may be explained by disturbances in prediction error-dependent learning. Here we set up complementary studies in order to examine whether such a disturbance also modulates memory reconsolidation and hence explains their remarkable persistence. First, we quantified individual brain responses to prediction error in a causal learning task in 18 human subjects (8 female). Next, a placebo-controlled within-subjects study of the impact of ketamine was set up on the same individuals. We determined the influence of this NMDA receptor antagonist (previously shown to induce aberrant prediction error signal and lead to transient alterations in perception and belief) on the evolution of a fear memory over a 72 hour period: they initially underwent Pavlovian fear conditioning; 24 hours later, during ketamine or placebo administration, the conditioned stimulus (CS) was presented once, without reinforcement; memory strength was then tested again 24 hours later. Re-presentation of the CS under ketamine led to a stronger subsequent memory than under placebo. Moreover, the degree of strengthening correlated with individual vulnerability to ketamine''s psychotogenic effects and with prediction error brain signal. This finding was partially replicated in an independent sample with an appetitive learning procedure (in 8 human subjects, 4 female). These results suggest a link between altered prediction error, memory strength and psychosis. They point to a core disruption that may explain not only the emergence of delusional beliefs but also their persistence.     

深度学习在药物活性预测研究中的应用

药物从研发到临床应用需要耗费较长的时间，研发期间的投入成本可高达十几亿元。而随着医药研发与人工智能的结合以及生物信息学的飞速发展，药物活性相关数据急剧增加，传统的实验手段进行药物活性预测已经难以满足药物研发的需求。借助算法来辅助药物研发，解决药物研发中的各种问题能够大大推动药物研发进程。传统机器学习方法尤其是随机森林、支持向量机和人工神经网络在药物活性方面能够达到较高的预测精度。深度学习由于具有多层神经网络，模型可以接收高维的输入变量且不需要人工限定数据输入特征，可以拟合较为复杂的函数模型，应用于药物研发可以进一步提高各个环节的效率。在药物活性预测中应用较为广泛的深度学习模型主要是深度神经网络（deep neural networks，DNN）、循环神经网络（recurrent neural networks，RNN）和自编码器（auto encoder，AE），而生成对抗网络（generative adversarial networks，GAN）由于其生成数据的能力常常被用来和其他模型结合进行数据增强。近年来深度学习在药物分子活性预测方面的研究和应用综述表明，深度学习模型的准确度和效率均高于传统实验方法和传统机器学习方法。因此，深度学习模型有望成为药物研发领域未来十年最重要的辅助计算模型。     

比较逻辑斯蒂与地理加权逻辑斯蒂回归模型在福建林火发生的适用性

林火预测预报是科学有效进行林火管理的前提,是林业管理部门和科研工作者的广泛关注的领域。逻辑斯蒂回归(Logistic Regression,LR)是目前国内外广泛应用于森林火灾预测的模型方法,然而近年来有学者发现该方法没有充分考虑林火影响因子的空间相关性和异质性,从而导致模型拟合结果偏差。地理加权逻辑斯蒂回归(Geographically weighted logistic regression,GWR)模型考虑到了模型变量之间的空间相关性,有效提高的模型的拟合能力。为探讨GWLR模型在福建林火预测上的适用性,本研究应用LR和GWLR两种方法分别建立福建省森林火灾与气象因子的预测模型,通过模型拟合能力对比,判断在GWLR的适用性。研究以2000—2005年福建地区森林火灾卫星火点数据和每日气象因子为基础,将全样本分为60%的建模数据和40%的校验数据,并重复5次,建立5个样本组。选择在5个样本组中3个及以上表现显著的变量进入最终模型。研究结果表明GWLR在模型拟合度、模型残差、空间自相关性以及预测准确率等方面均优于LR模型,说明充分考虑模型变量的空间异质性有助于提高模型的预测精度,同时也验证了GWLR在福建地区林火预测上的适应性。此外,模型参数结果显示,"日最高地表气温"、"日最低地表气温"、"日平均风速"、"24小时降水量"、"日最高本站气压"、"日照时数"、"日最高气温"和"日最小相对湿度"8个因子对福建省林火发生有显著影响,研究结论为福建地区林火预测预报提供了新的方法。     

Deep learning-based multi-task prediction system for plant disease and species detection

The manual prediction of plant species and plant diseases is expensive, time-consuming, and requires expertise that is not always available. Automated approaches, including machine learning and deep learning, are increasingly being applied to surmount these challenges. For this, accurate models are needed to provide reliable predictions and guide the decision-making process. So far, these two problems have been addressed separately, and likewise, separate models have been developed for each of these two problems, but considering that plant species and plant disease prediction are often related tasks, they can be considered together. We therefore propose and validate a novel approach based on the multi-task learning strategy, using shared representations between these related tasks, because they perform better than individual models. We apply a multi-input network that uses raw images and transferred deep features extracted from a pre-trained deep model to predict each plant's type and disease. We develop an end-to-end multi-task model that carries out more than one learning task at a time and combines the Convolutional Neural Network (CNN) features and transferred features. We then evaluate this model using public datasets. The results of our experiments demonstrated that this Multi-Input Multi-Task Neural Network model increases efficiency and yields faster learning for similar detection tasks.     

Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

Predicting residue-residue distance relationships (eg, contacts) has become the key direction to advance protein structure prediction since 2014 CASP11 experiment, while deep learning has revolutionized the technology for contact and distance distribution prediction since its debut in 2012 CASP10 experiment. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. Our experiment demonstrates that contact distance prediction and deep learning methods are the key reasons that MULTICOM was ranked 3rd out of all 98 predictors in both template-free and template-based structure modeling in CASP13. Deep convolutional neural network can utilize global information in pairwise residue-residue features such as coevolution scores to substantially improve contact distance prediction, which played a decisive role in correctly folding some free modeling and hard template-based modeling targets. Deep learning also successfully integrated one-dimensional structural features, two-dimensional contact information, and three-dimensional structural quality scores to improve protein model quality assessment, where the contact prediction was demonstrated to consistently enhance ranking of protein models for the first time. The success of MULTICOM system clearly shows that protein contact distance prediction and model selection driven by deep learning holds the key of solving protein structure prediction problem. However, there are still challenges in accurately predicting protein contact distance when there are few homologous sequences, folding proteins from noisy contact distances, and ranking models of hard targets.     

A deep learning approach to conflating heterogeneous geospatial data for corn yield estimation: A case study of the US Corn Belt at the county level

Understanding large‐scale crop growth and its responses to climate change are critical for yield estimation and prediction, especially under the increased frequency of extreme climate and weather events. County‐level corn phenology varies spatially and interannually across the Corn Belt in the United States, where precipitation and heat stress presents a temporal pattern among growth phases (GPs) and vary interannually. In this study, we developed a long short‐term memory (LSTM) model that integrates heterogeneous crop phenology, meteorology, and remote sensing data to estimate county‐level corn yields. By conflating heterogeneous phenology‐based remote sensing and meteorological indices, the LSTM model accounted for 76% of yield variations across the Corn Belt, improved from 39% of yield variations explained by phenology‐based meteorological indices alone. The LSTM model outperformed least absolute shrinkage and selection operator (LASSO) regression and random forest (RF) approaches for end‐of‐the‐season yield estimation, as a result of its recurrent neural network structure that can incorporate cumulative and nonlinear relationships between corn yield and environmental factors. The results showed that the period from silking to dough was most critical for crop yield estimation. The LSTM model presented a robust yield estimation under extreme weather events in 2012, which reduced the root‐mean‐square error to 1.47 Mg/ha from 1.93 Mg/ha for LASSO and 2.43 Mg/ha for RF. The LSTM model has the capability to learn general patterns from high‐dimensional (spectral, spatial, and temporal) input features to achieve a robust county‐level crop yield estimation. This deep learning approach holds great promise for better understanding the global condition of crop growth based on publicly available remote sensing and meteorological data.     

Assessment of protein model structure accuracy estimation in CASP13: Challenges in the era of deep learning

Scoring model structure is an essential component of protein structure prediction that can affect the prediction accuracy tremendously. Users of protein structure prediction results also need to score models to select the best models for their application studies. In Critical Assessment of techniques for protein Structure Prediction (CASP), model accuracy estimation methods have been tested in a blind fashion by providing models submitted by the tertiary structure prediction servers for scoring. In CASP13, model accuracy estimation results were evaluated in terms of both global and local structure accuracy. Global structure accuracy estimation was evaluated by the quality of the models selected by the global structure scores and by the absolute estimates of the global scores. Residue-wise, local structure accuracy estimations were evaluated by three different measures. A new measure introduced in CASP13 evaluates the ability to predict inaccurately modeled regions that may be improved by refinement. An intensive comparative analysis on CASP13 and the previous CASPs revealed that the tertiary structure models generated by the CASP13 servers show very distinct features. Higher consensus toward models of higher global accuracy appeared even for free modeling targets, and many models of high global accuracy were not well optimized at the atomic level. This is related to the new technology in CASP13, deep learning for tertiary contact prediction. The tertiary model structures generated by deep learning pose a new challenge for EMA (estimation of model accuracy) method developers. Model accuracy estimation itself is also an area where deep learning can potentially have an impact, although current EMA methods have not fully explored that direction.     

Stimulus-dependent adjustment of reward prediction error in the midbrain

Previous reports have described that neural activities in midbrain dopamine areas are sensitive to unexpected reward delivery and omission. These activities are correlated with reward prediction error in reinforcement learning models, the difference between predicted reward values and the obtained reward outcome. These findings suggest that the reward prediction error signal in the brain updates reward prediction through stimulus-reward experiences. It remains unknown, however, how sensory processing of reward-predicting stimuli contributes to the computation of reward prediction error. To elucidate this issue, we examined the relation between stimulus discriminability of the reward-predicting stimuli and the reward prediction error signal in the brain using functional magnetic resonance imaging (fMRI). Before main experiments, subjects learned an association between the orientation of a perceptually salient (high-contrast) Gabor patch and a juice reward. The subjects were then presented with lower-contrast Gabor patch stimuli to predict a reward. We calculated the correlation between fMRI signals and reward prediction error in two reinforcement learning models: a model including the modulation of reward prediction by stimulus discriminability and a model excluding this modulation. Results showed that fMRI signals in the midbrain are more highly correlated with reward prediction error in the model that includes stimulus discriminability than in the model that excludes stimulus discriminability. No regions showed higher correlation with the model that excludes stimulus discriminability. Moreover, results show that the difference in correlation between the two models was significant from the first session of the experiment, suggesting that the reward computation in the midbrain was modulated based on stimulus discriminability before learning a new contingency between perceptually ambiguous stimuli and a reward. These results suggest that the human reward system can incorporate the level of the stimulus discriminability flexibly into reward computations by modulating previously acquired reward values for a typical stimulus.