Efficient clustering in collaborative filtering recommender system: Hybrid method based on genetic algorithm and gravitational emulation local search algorithm

The ultimate goal of the Recommender System (RS) is to offer a proposal that is very close to the user's real opinion. Data clustering can be effective in increasing the accuracy of production proposals by the RS. In this paper, single-objective hybrid evolutionary approach is proposed for clustering items in the offline collaborative filtering RS. This method, after generating a population of randomized solutions, at each iteration, improves the population of solutions first by Genetic Algorithm (GA) and then by using the Gravitational Emulation Local Search (GELS) algorithm. Simulation results on standard datasets indicate that although the proposed hybrid meta-heuristic algorithm requires a relatively high run time, it can lead to more appropriate clustering of existing data and thus improvement of the Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Coverage criteria.     

A geospatial approach to monitoring impervious surfaces in watersheds using Landsat data (the Mondego Basin,Portugal as a case study)

The urbanization of watersheds is a highly dynamic global phenomenon that must be monitored. With consequences for the environment, the population, and the economy, accurate products at adequate spatial and temporal resolutions are required and demanded by the science community and stakeholders alike. To address these needs, a new Impervious Surface Area (ISA) product was created for a Portuguese Watershed (Mondego river) from Landsat data (a combination of leaf-on multispectral bands, derived products, and NDVI time series), using Regression Tree Models (RTM). The product provides 30-m spatial resolution ISA estimates (0–100%) with a Mean Average Error (MAE) of 1.6% and Root Mean Square Error (RMSE) of 5.5%.A strategy to update the baseline product was tested in earlier imagery (2001 and 2007) for a subset of the watershed. Instead of updating the baseline product, the strategy seeks to identify stable training samples and remove those where change was detected in a time series of Change Vector Analysis (CVA). The stable samples were then used to create new ISA models using RTM. The updated maps were similar to the original product in terms of accuracy metrics (MAE: 2001: 2.6%; 2007:3.6%).The products and methodology offer a new perspective on the urban development of the watershed, at a scale previously unavailable. It can also be replicated elsewhere at a low cost, leveraging the growing Landsat data archive, and provide timely information on relevant land cover metrics to the scientific community and stakeholders.     

A low footprint olive grove weather forecasting using a single-layered seasonal attention encoder-decoder model

Weather forecasting is essential in various applications such as olive smart farming. Farmers use the predicted weather data to take appropriate actions with the aim of increasing the crop production. Many deep learning models have been developed for tackling such a problem. However, olive groves are located in remote areas with no Internet connectivity, therefore these models are not applicable as they require either powerful processors or communication with cloud servers for inference. In this work, we propose a deep learning encoder-decoder model that uses a seasonal attention mechanism for time series forecasting of weather variables. The proposed model is non-complex, yet more powerful, compared to the more complex models in the literature. We use this model as the core of a framework that preprocess the training and testing data, train the model, and deploy the model on a resource-constrained microcontroller. Using real-life weather datasets of Spanish, Greek, and Chinese weather stations, we prove that the proposed model achieves a higher prediction accuracy compared to the existing literature. More specifically, the achieved prediction mean absolute error (MAE) is 2.13 °C and root mean squared error (RMSE) is 2.64 °C. This outstanding accuracy performance is achieved with the model requiring only 37.6 kB of memory for storing the model parameters with a total memory requirement of 50.1 kB. Since the model is relatively non-complex, we implement it on the Raspberry Pi Pico platform which has a very low cost with minimal power consumption compared to other embedded platforms. We also build a prototype and test it to verify the model's ability to achieve the target objective in real-life scenarios.     

Akaike information criterion should not be a “test” of geographical prediction accuracy in ecological niche modelling

Model complexity in ecological niche modelling has been recently considered as an important issue that might affect model performance. New methodological developments have implemented the Akaike information criterion (AIC) to capture model complexity in the Maxent algorithm model. AIC is calculated based on the number of parameters and likelihoods of continuous raw outputs. ENMeval R package allows users to perform a species-specific tuning of Maxent settings running models with different combinations of regularization multiplier and feature classes and finally, all these models are compared using AIC corrected for small sample size. This approach is focused to find the “best” model parametrization and it is thought to maximize the model complexity and therefore, its predictability. We found that most niche modelling studies examined by us (68%) tend to consider AIC as a criterion of predictive accuracy in geographical distribution. In other words, AIC is used as a criterion to choose those models with the highest capacity to discriminate between presences and absences. However, the link between AIC and geographical predictive accuracy has not been tested so far. Here, we evaluated this relationship using a set of simulated (virtual) species. We created a set of nine virtual species with different ecological and geographical traits (e.g., niche position, niche breadth, range size) and generated different sets of true presences and absences data across geography. We built a set of models using Maxent algorithm with different regularization values and features schemes and calculated AIC values for each model. For each model, we obtained binary predictions using different threshold criteria and validated using independent presence and absences data. We correlated AIC values against standard validation metrics (e.g., Kappa, TSS) and the number of pixels correctly predicted as presences and absences. We did not find a correlation between AIC values and predictive accuracy from validation metrics. In general, those models with the lowest AIC values tend to generate geographical predictions with high commission and omission errors. The results were consistent across all species simulated. Finally, we suggest that AIC should not be used if users are interested in prediction more than explanation in ecological niche modelling.     

基于均匀设计的主成分分析-支持向量机模型及其在几丁质酶最适pH建模中的应用

采用主成分分析法对样本数据集进行预处理,将得到的新样本数据集输入支持向量机,籍均匀设计,构建了几丁质酶氨基酸组成和最适pH的数学模型。当惩罚系数C为10,epsilon值为0.7,Gamma值为0.5,模型对pH值拟合的平均绝对百分比误差为3.76%,同时具有良好的预测效果,预测的平均绝对误差为0.42个pH单位。该方法比用BP神经网络方法效果更佳。     

西藏自治区草地地上生物量遥感反演研究

草地地上生物量（Aboveground Biomass,AGB）是反映草地生态系统功能和质量的关键指标,大尺度地准确估算草地AGB对草地生态系统经营管理至关重要。研究以MODIS影像为数据源,提取反射率、植被指数和植被产品三种不同类型的特征变量,结合野外实测样地草地AGB数据,构建以多元线性逐步回归为代表的参数模型以及随机森林、支持向量机和kNN等非参数模型进行西藏自治区草地AGB估测及空间分布制图。结果表明：（1）多元线性逐步回归、随机森林、支持向量机和kNN模型在加入植被产品特征变量后,RMSE分别降低了15.8%、13.5%、4.1%和17.3%,表明植被产品作为建模变量用于草地AGB估测可有效提高模型精度;（2）三种组合变量构建的草地AGB估测模型中,反射率、植被指数、植被产品组合构建的模型效果最佳,其中kNN模型估测精度最高,R²达到0.60,RMSE和MAE分别为0.43、0.34 t/hm²;（3）草地AGB空间分布呈现出西北地区较低、中部地区较高且分布形态较破碎和东部地区较高的变化特征;（4）利用MODIS植被产品结合kNN模型的预测值与草地实测的AGB空间分布趋势基本一致。综上,MODIS植被产品结合kNN模型可作为大尺度区域草地AGB遥感估测的有效参考。     

木聚糖酶氨基酸组成与其最适pH的神经网络模型

籍均匀设计（UD）方法,构建了G/11家族木聚糖酶氨基酸组成和最适pH的神经网络（NNs）模型。当学习速率为0.09、动态参数为0.4、Sigmoid参数为0.98,隐含层结点数为10时,该模型对最适pH的拟合和预测平均绝对百分比误差可分别达到3.02%和4.06%,均方根误差均为0.19个pH单位,平均绝对误差分别为0.11和0.19个pH单位。该结果比文献报道的用逐步回归方法好。     

A spatially-explicit model of alien plant richness in Tenerife (Canary Islands)

Biological invasions are one of the major threats to biodiversity, especially in oceanic islands. In the Canary Islands, the relationships between plant Alien Species Richness (ASR) and their environmental and anthropogenic determinants were thoroughly investigated using ecological models. However, previous predictive models rarely accounted for spatial autocorrelation (SAC) and uncertainty of predictions, thus missing crucial information related to model accuracy and predictions reliability. In this study, we propose a Generalized Linear Spatial Model (GLSM) for ASR under a Bayesian framework on Tenerife Island. Our aim is to test whether the inclusion of SAC into the modelling framework could improve model performance resulting in more reliable predictions. Results demonstrated as accounting for SAC dramatically reduced the model's AIC (ΔAIC = 4423) and error magnitudes, showing also better performances in terms of goodness of fit. Calculation of uncertainty related to predicted values pointed out those areas where either the number of observations (e.g. under-sampled areas) or the reliability of the environmental predictors was lower (e.g. low spatial resolution in highly heterogeneous environments). Although our results confirmed what was already observed in other ecological studies, such as the important role of roads in ASR spread, methodological considerations on the applied modelling approach point out the importance of considering spatial autocorrelation and researcher's prior knowledge to increase the predictive power of statistical models as well as the correctness in terms of coefficients estimates. The proposed approach may serve as an essential management tools highlighting those portions of territory that will be more prone to biological invasions and where monitoring efforts should be addressed.     

基于辅助环境变量的土壤有机碳空间插值——以黄土丘陵区小流域为例

利用普通克里格法(OK)、反距离加权法(IDW)、径向基函数法(RBF)、基于土地利用类型修正的普通克里格法(OK_LU)4种插值方法,对黄土丘陵羊圈沟小流域的土壤有机碳含量进行空间插值。预测结果的准确性通过Pearson相关系数(R),平均绝对误差(MAE),均方根误差(RMSE),准确度(AC)来评价。研究结果表明:(1)在前3种常规空间插值方法中,OK对刻画区域土壤有机碳的空间分布趋势效果最佳,其预测MAE值和RMSE值均为最小,Pearson相关系数(R)和准确度(AC)最大,说明其预测结果的准确性最好、预测的极端误差也最小;其次为RBF;IDW预测的效果最差。(2)OK_LU在空间特征表达方面能够更好地反映复杂地形区的局部变异,其插值结果的精度相比OK有一定程度的提高,其平均绝对误差(MAE)从0.900%降到了0.567%,均方根误差(RMSE)从1.101%降到了0.777%,Pearson相关系数(R)从0.4026提高到0.5589,准确度(AC)从0.9081提高到0.9505。综合比较,在黄土丘陵地区,OK_LU能使插值结果的精度有较大提高,是土壤有机碳空间制图的有效途径。     

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.     

Comparison of non-linear models to describe the lactation curves for milk yield and composition in buffaloes (Bubalus bubalis)

In order to describe the lactation curves of milk yield (MY) and composition in buffaloes, seven non-linear mathematical equations (Wood, Dhanoa, Sikka, Nelder, Brody, Dijkstra and Rook) were used. Data were 116 117 test-day records for MY, fat (FP) and protein (PP) percentages of milk from the first three lactations of buffaloes which were collected from 893 herds in the period from 1992 to 2012 by the Animal Breeding Center of Iran. Each model was fitted to monthly production records of dairy buffaloes using the NLIN and MODEL procedures in SAS and the parameters were estimated. The models were tested for goodness of fit using adjusted coefficient of determination root means square error (RMSE), Durbin–Watson statistic and Akaike’s information criterion (AIC). The Dijkstra model provided the best fit of MY and PP of milk for the first three parities of buffaloes due to the lower values of RMSE and AIC than other models. For the first-parity buffaloes, Sikka and Brody models provided the best fit of FP, but for the second- and third-parity buffaloes, Sikka model and Brody equation provided the best fit of lactation curve for FP, respectively. The results of this study showed that the Wood and Dhanoa equations were able to estimate the time to the peak MY more accurately than the other equations. In addition, Nelder and Dijkstra equations were able to estimate the peak time at second and third parities more accurately than other equations, respectively. Brody function provided more accurate predictions of peak MY over the first three parities of buffaloes. There was generally a positive relationship between 305-day MY and persistency measures and also between peak yield and 305-day MY, calculated by different models, within each lactation in the current study. Overall, evaluation of the different equations used in the current study indicated the potential of the non-linear models for fitting monthly productive records of buffaloes.     

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.     

基于机器学习算法的草地地上生物量估测——以祁连山草地为例

草地地上生物量（Aboveground Biomass,AGB）是指导畜牧业生产管理的重要指标,是草畜平衡综合分析的基础。目前,有关祁连山草地AGB反演的研究较少,且多源数据间的尺度差异问题并未得到很好的解决。为了解祁连山草地AGB的空间分布状况,利用Sentinel-2多光谱数据、无人机（Unmanned Aerial Vehicle,UAV）数据以及2021年植被生长期实测草地AGB数据实现了空天地一体化监测,通过决策树回归（Decision Tree Regression,DTR）、随机森林回归（Random Forest Regression,RFR）、梯度提升决策回归树（Gradient Boosting Regression Tree,GBRT）以及极致梯度提升（eXtreme Gradient Boosting,XGBoost）共4种算法反演草地AGB的适用性分析,利用最优模型反演了祁连山草地的AGB空间分布状况。结果表明：研究区内多种植被指数所表现出的特性有所差异。祁连山地区AGB在空间分布上呈现出由西北向东南递增的趋势,平均AGB为925.43kg/hm²。6种植被指数与实测AGB之间均表现为显著正相关,适合作为祁连山草地AGB遥感反演的指标;XGBoost模型较其它模型具有最高的R²值（0.78）和精度（74.75%）、最低的均方根误差（RMSE,99.74 kg/hm²）和平均绝对误差（MAE,71.60 kg/hm²）,模型反演效果最好;UAV数据能够提供更加详细的空间细节特征,减小Sentinel-2数据和实地采样数据间的尺度差异;因此,基于6种植被指数与祁连山草地AGB间的相关性,构建XGBoost模型反演研究区草地AGB空间分布状况是具有实践意义的。研究结果将为指导祁连山草地畜牧业的发展和维护草地生态系统的平衡提供一定的参考价值与数据支撑。     

A machine vision system to predict individual cow feed intake of different feeds in a cowshed

Data on individual feed intake of dairy cows, an important variable for farm management, are currently unavailable in commercial dairies. A real-time machine vision system including models that are able to adapt to multiple types of feed was developed to predict individual feed intake of dairy cows. Using a Red-Green-Blue-Depth (RGBD) camera, images of feed piles of two different feed types (lactating cows' feed and heifers' feed) were acquired in a research dairy farm, for a range of feed weights under varied configurations and illuminations. Several models were developed to predict individual feed intake: two Transfer Learning (TL) models based on Convolutional Neural Networks (CNNs), one CNN model trained on both feed types, and one Multilayer Perceptron and Convolutional Neural Network model trained on both feed types, along with categorical data. We also implemented a statistical method to compare these four models using a Linear Mixed Model and a Generalised Linear Mixed Model, showing that all models are significantly different. The TL models performed best and were trained on both feeds with TL methods. These models achieved Mean Absolute Errors (MAEs) of 0.12 and 0.13 kg per meal with RMSE of 0.18 and 0.17 kg per meal for the two different feeds, when tested on varied data collected manually in a cowshed. Testing the model with actual cows’ meals data automatically collected by the system in the cowshed resulted in a MAE of 0.14 kg per meal and RMSE of 0.19 kg per meal. These results suggest the potential of measuring individual feed intake of dairy cows in a cowshed using RGBD cameras and Deep Learning models that can be applied and tuned to different types of feed.     

Visual representation of DNA sequences for exon detection using non-parametric spectral estimation techniques

This paper presents a new approach for modeling of DNA sequences for the purpose of exon detection. The proposed model adopts the sum-of-sinusoids concept for the representation of DNA sequences. The objective of the modeling process is to represent the DNA sequence with few coefficients. The modeling process can be performed on the DNA signal as a whole or on a segment-by-segment basis. The created models can be used instead of the original sequences in a further spectral estimation process for exon detection. The accuracy of modeling is evaluated evaluated by using the Root Mean Square Error (RMSE) and the R-square metrics. In addition, non-parametric spectral estimation methods are used for estimating the spectral of both original and modeled DNA sequences. The results of exon detection based on original and modeled DNA sequences coincide to a great extent, which ensures the success of the proposed sum-of-sinusoids method for modeling of DNA sequences.     

Prediction of daily global solar radiation and air temperature using six machine learning algorithms; a case of 27 European countries

The prediction of global solar radiation in a region is of great importance as it provides investors and politicians with more detailed knowledge about the solar resource of that region, which can be very beneficial for large-scale solar energy development. In this sense, the main objective of this study is to predict the daily global solar radiation data of 27 cities (Brussels, Paris, Lisbon, Madrid…), located in 27 countries, which have mostly different solar radiation distributions in Europe. In this research, six different machine-learning algorithms (Linear model (LM), Decision Tree (DT), Support Vector Machine (SVM), Deep Learning (DL), Random Forest (RF) and Gradient Boosted Trees (GBT)) are used. In the training of these algorithms, daily air temperature(Ta), wind speed(Va), relative humidity(RH) and solar radiation of these cities are used. The data is supplied from the Meteonorm tool and cover the last years grouped in two periods (1960–1990; 2000–2019). To decide on the success of these algorithms, four different statistical metrics (Average Relative Error (ARE), Average absolute Error (AAE), Root Mean Squared Error (RMSE), and R² (R-Squared)) are discussed in the study. In addition, the forecasting of air temperature and global solar radiation of these cities in 2050 and 2100 were made using three of the most recent Intergovernmental Panel on Climate Change (IPCC) scenarios (RCP2.6; RCP 4.5, and RCP 8.5). The results show that ARE, R,² and RMSE values of all algorithms are ranging from 0.114 to 6.321, from 0.382 to 0.985, from 0.145 to 2.126 MJ/m², respectively. By analysing all the algorithms, it is noticed that the Decision tree exhibited the worst result in terms of R,² and RMSE metrics. Among the six prediction algorithms, the DL was recognized as the only algorithm that exceeded the t-critical value (The t-critical value is the cutoff between retaining or rejecting the null hypothesis). Globally, all the six machine learning algorithms used in this research can be applied to predict the daily global solar radiation data with good accuracy. Despite this, the SVM model is the best model among all the six models used. It is followed by the DL, LM, GB, RF and DT, respectively.     

帽儿山阔叶混交林天然更新幼苗幼树地径-树高模型

基于黑龙江省东北林业大学帽儿山实验林场48块天然阔叶林幼苗幼树调查数据,在8个备选模型中为主要更新树种选择最佳地径(D₀)-树高(H)模型作为基本模型,通过再参数化在基础模型中引入林分因子,并建立样地水平混合效应模型,最后分别对基础模型和混合效应模型进行独立样本检验.结果表明:各树种幼苗幼树的地径-树高关系存在明显的正相关,幂函数或包含幂函数的模型能较好地拟合幼苗幼树地径和树高的关系;基础模型中引入林分因子[林分优势高(H_T)、林分平均胸径(D_g)、林分胸高断面积(BA)]能提高模型的拟合效果,各树种剩余均方根误差(RMSE)下降1.3%～7.4%(平均3.8%),但调整后的决定系数(R_a²)仅仅提高0.1%～1.1%(平均0.6%),赤池信息准则(AIC)下降3.2%～35.2%(平均下降11.4%).对春榆、椴树、水曲柳等10个树种建立混合效应模型,混合效应模型的R_a²比基础模型有所提高,增幅为0.5%～3.5%(平均增加2.2%);RMSE和AIC比基础模型的小,RMSE下降的幅度很大,为3.9%～20.3%,平均下降13.9%,AIC减少4.0%～44.4%(平均减少22.3%).模型检验结果显示,相对于基础模型,混合效应模型的平均绝对误差(MAE)减小0.0001～0.46 m,平均减小0.08 m;平均预测误差百分比(MPSE)降幅较大,为0.1%～6.2%,平均降幅2.0%.说明混合效应模型既能提高模型的拟合效果,又能提高模型的预测能力.本研究构建的阔叶混交林主要更新树种幼苗幼树地径-树高模型为天然阔叶林结构分析和林分生长预测提供了参考.     

基于环境星与MODIS时序数据的面向对象森林植被分类

林区地形复杂、植被分布无序,且森林植被光谱信息相近,因而森林二级类型边界的确定成为土地覆盖遥感分类的难点。选择吉林省东部山区为研究区,以环境星影像(HJ-1 CCD)和中等分辨率成像光谱仪(MODIS)时序数据为基础,采用面向对象的分类方法进行森林植被类型的提取。分类特征参数主要选取了HJ-1 CCD的光谱和纹理特征,以及MODIS时序数据的物候特征。研究区总体分类精度为91.5%,Kappa系数为0.88,森林二级类型的分类精度均较高,其中落叶阔叶林的制图精度达到了97.1%。所用的面向对象分类方法与未加入物候特征的面向对象分类方法相比,森林二级类型的分类精度得到大幅度提高。     

On observation distributions for state space models of population survey data

1.?State space models are starting to replace more simple time series models in analyses of temporal dynamics of populations that are not perfectly censused. By simultaneously modelling both the dynamics and the observations, consistent estimates of population dynamical parameters may be obtained. For many data sets, the distribution of observation errors is unknown and error models typically chosen in an ad-hoc manner. 2.?To investigate the influence of the choice of observation error on inferences, we analyse the dynamics of a replicated time series of red kangaroo surveys using a state space model with linear state dynamics. Surveys were performed through aerial counts and Poisson, overdispersed Poisson, normal and log-normal distributions may all be adequate for modelling observation errors for the data. We fit each of these to the data and compare them using AIC. 3.?The state space models were fitted with maximum likelihood methods using a recent importance sampling technique that relies on the Kalman filter. The method relaxes the assumption of Gaussian observation errors required by the basic Kalman filter. Matlab code for fitting linear state space models with Poisson observations is provided. 4.?The ability of AIC to identify the correct observation model was investigated in a small simulation study. For the parameter values used in the study, without replicated observations, the correct observation distribution could sometimes be identified but model selection was prone to misclassification. On the other hand, when observations were replicated, the correct distribution could typically be identified. 5.?Our results illustrate that inferences may differ markedly depending on the observation distributions used, suggesting that choosing an adequate observation model can be critical. Model selection and simulations show that for the models and parameter values in this study, a suitable observation model can typically be identified if observations are replicated. Model selection and replication of observations, therefore, provide a potential solution when the observation distribution is unknown.     

两种预测模型在地下水动态中的比较与应用

预测陕西洛惠渠灌区地下水动态变化情况,在综合分析了各种地下水动态研究方法的基础上,提出了基于支持向量机和改进的BP神经网络模型的灌区地下水动态预测方法,并在MATLAB中编制了相应的计算机程序,建立了相应的地下水动态预测模型。以灌区多年实例数据为学习样本和测试样本,比较了两种模型的地下水动态预测优劣性。研究表明,支持向量机模型和BP网络模型在样本训练学习过程中都具较高的模拟精度,而在样本学习阶段,支持向量机的预测精度明显优于BP网络,可以很好的描述地下水动态复杂的耦合关系。支持向量机方法切实可行,更加适合大型灌区地下水动态预测,是对传统地下水动态研究方法的补充与完善。