共查询到20条相似文献，搜索用时 140 毫秒
1.
The objective of this study is to make a comparison of the prediction performance of three techniques, Functional Trees (FT), Multilayer Perceptron Neural Networks (MLP Neural Nets), and Naïve Bayes (NB) for landslide susceptibility assessment at the Uttarakhand Area (India). Firstly, a landslide inventory map with 430 landslide locations in the study area was constructed from various sources. Landslide locations were then randomly split into two parts (i) 70 % landslide locations being used for training models (ii) 30 % landslide locations being employed for validation process. Secondly, a total of eleven landslide conditioning factors including slope angle, slope aspect, elevation, curvature, lithology, soil, land cover, distance to roads, distance to lineaments, distance to rivers, and rainfall were used in the analysis to elucidate the spatial relationship between these factors and landslide occurrences. Feature selection of Linear Support Vector Machine (LSVM) algorithm was employed to assess the prediction capability of these conditioning factors on landslide models. Subsequently, the NB, MLP Neural Nets, and FT models were constructed using training dataset. Finally, success rate and predictive rate curves were employed to validate and compare the predictive capability of three used models. Overall, all the three models performed very well for landslide susceptibility assessment. Out of these models, the MLP Neural Nets and the FT models had almost the same predictive capability whereas the MLP Neural Nets (AUC = 0.850) was slightly better than the FT model (AUC = 0.849). The NB model (AUC = 0.838) had the lowest predictive capability compared to other models. Landslide susceptibility maps were final developed using these three models. These maps would be helpful to planners and engineers for the development activities and land-use planning. 相似文献
2.
The aim of this study was to have a comparative investigation and evaluation of the capabilities of correlative and mechanistic modeling processes, applied to the projection of future distributions of date palm in novel environments and to establish a method of minimizing uncertainty in the projections of differing techniques. The location of this study on a global scale is in Middle Eastern Countries. We compared the mechanistic model CLIMEX (CL) with the correlative models MaxEnt (MX), Boosted Regression Trees (BRT), and Random Forests (RF) to project current and future distributions of date palm (Phoenix dactylifera L.). The Global Climate Model (GCM), the CSIRO-Mk3.0 (CS) using the A2 emissions scenario, was selected for making projections. Both indigenous and alien distribution data of the species were utilized in the modeling process. The common areas predicted by MX, BRT, RF, and CL from the CS GCM were extracted and compared to ascertain projection uncertainty levels of each individual technique. The common areas identified by all four modeling techniques were used to produce a map indicating suitable and unsuitable areas for date palm cultivation for Middle Eastern countries, for the present and the year 2100. The four different modeling approaches predict fairly different distributions. Projections from CL were more conservative than from MX. The BRT and RF were the most conservative methods in terms of projections for the current time. The combination of the final CL and MX projections for the present and 2100 provide higher certainty concerning those areas that will become highly suitable for future date palm cultivation. According to the four models, cold, hot, and wet stress, with differences on a regional basis, appears to be the major restrictions on future date palm distribution. The results demonstrate variances in the projections, resulting from different techniques. The assessment and interpretation of model projections requires reservations, especially in correlative models such as MX, BRT, and RF. Intersections between different techniques may decrease uncertainty in future distribution projections. However, readers should not miss the fact that the uncertainties are mostly because the future GHG emission scenarios are unknowable with sufficient precision. Suggestions towards methodology and processing for improving projections are included. 相似文献
3.
基于2008—2019年我国台风县(区)灾情的直接经济损失数据,根据经济损失率将台风灾害经济损失风险分为五类,考虑台风灾害的致灾因子和孕灾环境因子共选取10个解释变量,采用五种经典的机器学习算法,包括支持向量机(Support Vector Machine,SVM)、随机森林(Random Forest,RF)、AdaBoost、XGBoost(Extreme Gradient Boosting Machine)和LightGBM(Light Gradient Boosting Machine),分别构建台风灾害经济损失风险评估模型,选出准确率最高的模型,应用于经典台风过程并进行检验评估。结果表明:基于RF算法的台风灾害经济损失风险模型的准确率最高;利用RF、XGBoost、LightGBM、AdaBoost和SVM算法构建模型的准确率依次为0.69、0.63、0.62、0.45和0.41。选择RF算法构建的台风灾害经济损失风险模型的解释变量表明,致灾因子是最主要的解释变量,其中,降雨导致损失的重要性超过风速。该模型在训练集和测试集上对风险分类的TS评分为0.55和0.51,但对每种风险类别的辨别能力存在差异,对于最低风险和最高风险的分类效果较好,对于较高风险和中等风险的分类能力不足。利用该模型对2017年第13号台风“天鸽”的经济损失进行检验评估,评估结果与实际台风灾害经济损失的风险等级较一致,各风险等级的准确率均达到0.7以上,TS评分在0.58以上,空报率和漏报率分别在0.31和0.25以下。 相似文献
4.
Solar radiation is an essential and important variable to many models. However, it is measured at a very limited number of meteorological stations in the world. Developing method for accurate estimation of solar radiation from measured meteorological variables has been a focus and challenging task. This paper presents the method of solar radiation estimation using support vector machine (SVM). The main objective of this work is to examine the feasibility of SVM and explore its potential in solar radiation estimation. A total of 20 SVM models using different combinations of sunshine ratio, maximum and minimum air temperature, relative humidity, and atmospheric water vapor pressure as input attributes are explored using meteorological data at 15 stations in China. These models significantly outperform the empirical models with an average 14 % higher accuracy. When sunshine duration data are available, model SVM2 using sunshine ratio and air temperature range is proposed. It significantly outperforms the empirical models with an average 26 % higher accuracy. When sunshine duration data are not available, model SVM19 using maximum temperature, minimum temperature and atmospheric water vapor pressure is proposed. It significantly outperforms the temperature-based empirical models with an average of 18 % higher accuracy. The remarkable improvement indicates that the SVM method would be a promising alternative over traditional approaches for estimation of solar radiation at any locations. 相似文献
5.
Farzin Shabani Lalit Kumar Subhashni Taylor 《Theoretical and Applied Climatology》2014,118(3):553-567
This study set out to model potential date palm distribution under current and future climate scenarios using an emission scenario, in conjunction with two different global climate models (GCMs): CSIRO-Mk3.0 (CS), and MIROC-H (MR), and to refine results based on suitability under four nonclimatic parameters. Areas containing suitable physicochemical soil properties and suitable soil taxonomy, together with land slopes of less than 10° and suitable land uses for date palm (Phoenix dactylifera) were selected as appropriate refining tools to ensure the CLIMEX results were accurate and robust. Results showed that large regions of Iran are projected as likely to become climatically suitable for date palm cultivation based on the projected scenarios for the years 2030, 2050, 2070, and 2100. The study also showed CLIMEX outputs merit refinement by nonclimatic parameters and that the incremental introduction of each additional parameter decreased the disagreement between GCMs. Furthermore, the study indicated that the least amount of disagreement in terms of areas conducive to date palm cultivation resulted from CS and MR GCMs when the locations of suitable physicochemical soil properties and soil taxonomy were used as refinement tools. 相似文献
6.
T. O. Odekunle E. E. Balogun O. O. Ogunkoya 《Theoretical and Applied Climatology》2005,81(1-2):101-112
Summary This study examined the rainfall onset and retreat dates between 1962 and 1996 in Nigeria, and generated models for their prediction. The study used the composite of rainfall-promoting factors namely, sea surface temperature of the tropical Atlantic Ocean, land/sea thermal contrast between some selected locations in Nigeria and the tropical Atlantic Ocean, surface location of the Inter-tropical Discontinuity and the land surface temperature in the selected locations in Nigeria. Rainfall and temperature data were collected from Ikeja, Benin, Ibadan, Ilorin, Kaduna and Kano, in Nigeria. Cumulative percentage mean rainfall was employed to generate the rainfall onset and retreat dates series, while the method of stepwise multiple regression analysis was used to construct the required prediction models.The results obtained showed that the hypothesized rainfall-promoting factors are efficient in predicting rainfall onset and retreat dates in Nigeria. The correlation coefficients (R2) obtained are in most cases (>75%) higher than 0.50 (with several of them approaching 0.90). Sea surface temperature and land/sea thermal contrast are the most significant predictor variables. The results also indicated that all the areas of the tropical Atlantic Ocean, from the Gulf of Guinea, through St Helena and Ascension Island, up to the Benguela Current region, influence the inter-annual variability in the rainfall onset and retreat dates of Nigeria. 相似文献
7.
Sea and Lake Breezes: A Review of Numerical Studies 总被引：11，自引：0，他引：11
Numerical studies of sea and lake breezes are reviewed. The modelled dependence of sea-breeze and lake-breeze characteristics
on the land surface sensible heat flux, ambient geostrophic wind, atmospheric stability and moisture, water body dimensions,
terrain height and slope, Coriolis parameter, surface roughness length, and shoreline curvature is discussed. Consensus results
on the influence of these geophysical variables on sea and lake breezes are synthesized as well as current gaps in our understanding.
A brief history of numerical modelling, an overview of recent high-resolution simulations, and suggestions for future research
related to sea and lake breezes are also presented. The results of this survey are intended to be a resource for numerical
modelling, coastal air quality, and wind power studies. 相似文献
8.
青藏高原东坡陡峭地形区是气候模式陆地降水模拟偏差的大值区,且这一偏差长期未得到有效改善.基于17个参加国际耦合模式比较计划第六阶段(CMIP6)的全球气候模式的日降水结果,评估了当前最新一代的气候模式对青藏高原东坡地区2000—2014年暖季(5—9月)降水气候态及其季节内演变的模拟能力.结果表明:高原东坡降水正偏差存... 相似文献
9.
10.
11.
In this research the dynamic downscaling method by Regional Climate Model (RegCM4.5) was used to assess the performance and sensitivity of seasonal simulated North and West of Iran (NI&WI) climate factors to different convection schemes, and transforms the large-scale simulated climate variables into land surface states over the North of Iran (NI) and West of Iran (WI). A 30-year (1986–2015) numerical integration simulation of climate over NI&WI was conducted using the regional climate model RegCM4.5 nested in one-way ERA-Interim reanalysis data. The Grell, Kuo and MIT-Emanuel cumulus convection with Holtslag and University of Washington (UW) planetary boundary layer (PBL) parameterization schemes were applied in the running of RegCM4.5 to test their capability in simulating precipitation and temperature in winter-spring (January–April) over NI and WI. The results demonstrated that the RegCM4.5 model has a good potential for simulating the variables and trend of surface temperature over the NI and WI region. Magnitude of the model bias for land surface temperature over different regions of Iran varies by convection parameterization schemes. In most cases, the root mean square error between post-processed simulated seasonal average temperature and observation value was less than 1 °C, but there is a systematic “cold bias”. In general, with respect to land surface temperature simulations, a better performance is obtained when using post-processing model’s data with Holtslag PBL-Grell and Holtslag PBL-Kuo configuration schemes, compared to the other simulations, over the NI&WI region. Also, the UW PBL convection schemes show a relatively excellent spatial correlations and normalized standard deviations closer to 1 for thirty-year seasonal land surface temperature anomalies over the entire NI&WI region. However, the simulation accuracy of model for precipitation is not as optimal as for temperature. The dominant feature in model simulations is a dry bias with the largest average value (∼1.04 mm/day) over NI region, while the lowest mean bias precipitation (∼−0.47 mm/day), mainly located in WI region. In the comparison of six configuration convection schemes, the Emanuel scheme has been proven to be the most accurate for simulating winter-spring seasonal mean precipitation over NI&WI region. The accuracy of the scheme also showed great difference in simulated station interpolation of precipitation, which urges the improvement for the simulation capability of spatial distribution of precipitation. In general, for seasonal variation of precipitation, the Emanuel convection with two (Holtslag, UW) PBL configuration schemes outperforms with a good correlation score between 0.7−0.8 and normalized standard deviations closer to 1. 相似文献
12.
Summary The aim of this study is the evaluation of models that estimate daily global solar radiation on tilted surfaces from that
measured on horizontal surfaces. Global solar radiation incident on a tilted plane consists of three components: beam radiation,
diffuse radiation and reflected radiation from the ground.
The Klein (1977) method, modified by Andersen (1980), was used for estimating direct solar radiation incident on tilted surfaces
and an isotropic model was used for estimating reflected solar radiation incident on a tilted plane. In contrast models for
the diffuse radiation component show major differences, which justifies a validation study which has been done.
Eight models for derivation of daily slope diffuse irradiance from daily horizontal diffuse irradiance were tested against
recorded slope irradiances at Karaj (35°55′ N; 50°56′ E), Iran. The following models were included: Badescu (2002), Tian et
al. (2001), Reindl et al. (1990), Skartveit and Olseth (1986), Koronakis (1986), Steven and Unsworth (1980), Hay (1979) and
Liu and Jordan (1962).
All the models use the same method for calculating beam radiation as well as ground reflected radiation. However, only diffuse
component of radiation was compared. Statistical indices showed that Reindl’s model gives the most accurate prediction for
the south-facing surface and Koronakis’s model performs best for the west-facing surface. The Relative Root Mean Square Errors
(%RMSE), except for Steven and Unsworth’s model that has unacceptable results, for whole data range from 1.02 to 10.42%. In
general, Reindl’s model produces the best agreement with the measured tilted data. 相似文献
13.
Developing a climate model for Iran using GIS 总被引：1，自引：0，他引：1
Summary In order to develop a climate model for Iran, monthly mean climatic variables from 117 synoptic stations were obtained from
the Iranian Meteorological Organisation. These variables were reduced to six orthogonal factors using factor analysis. The
stations were then divided into six groups using cluster analysis. Within each climatic group, the lowest and highest thresholds
for each factor were identified. The factor scores of the stations within each factor were interpolated across the country
applying Inverse Squared Distance Weight in the ArcGIS environment. Based on the factor scores, six conditional functions
were defined to allocate each pixel to a region. In order to simplify the models, one index variable was substituted for each
factor. Then, through Discriminant Analysis, the constants and coefficients of the models were determined. The final models
were evaluated against some examples, one of which, Yazd, was demonstrated fully.
Authors’ address: Bohloul Alijani, Manijeh Ghohroudi, Nahid Arabi, Department of Geography, Teacher Training University, Mofetteh
Avenue, Tehran, Iran. 相似文献
14.
基于C4.5算法的长江中下游地区夏季降水预测模型研究及应用 总被引：2，自引：0，他引：2
为了对长江中下游夏季降水进行短期气候预测,利用国家气候中心提供的74项环流指数和NOAA整编的西太平洋型WP指数、MEI指数、ENSO指数等多种全球环流指数资料,归纳整理了影响长江中下游夏季降水的34个前期春季因子,讨论了前期春季因子与夏季降水的关系,并利用这34个前期春季因子通过数据挖掘中的C4.5算法对1951—2013年(63 a)长江中下游夏季降水,建立判别降水偏多以及偏少的两类决策树预测模型,并分别得到5条和7条综合判别规则。随机选取80%左右历史年份数据作为模型的训练集,两模型的训练集准确率分别为94.12%和93.88%,剩余20%年份数据作为模型测试集,模型的测试预测准确率分别达91.67%和85.71%。模型预测应用也显示结果正确。模型研究和应用显示,基于C4.5算法的长江中下游夏季降水预测模型具有较高的预测准确率,模型构建合理有效,判别规则依据大数据理论,广泛考虑相关因子以及因子的排列组合,智能化选择关键因子,易于客观化、自动化实施,为长江流域汛期降水的短期气候预测提供了新的思路与方法。 相似文献
15.
中尺度对流系统（Mesoscale Convective System,MCS）是很多对流性天气的主要致灾体,可导致严重的气象和水文灾害,如雷暴大风、冰雹、龙卷风和山洪。对MCS进行准确的识别和追踪,并根据追踪轨迹及获得的MCS特征实现MCS的分类,对灾害天气的分析和预报有重要意义。基于京津冀地区2010—2019年的雷达组合反射率拼图资料,分别使用支持向量机（SVM）、随机森林（RF）、极度梯度提升决策树（XGBoost）和深度神经网络（DNN）4种机器学习方法,研发了京津冀地区MCS的自动识别算法。使用时、空重叠追踪法对识别的MCS进行追踪匹配,得到包含强度、时间和空间信息的MCS追踪数据资料。在区分线状对流系统和非线状对流系统的基础上,进一步从经典的尾随层云（Trailing Stratiform,TS）、前导层云（Leading Stratiform,LS）和平行层云（Parallel Stratiform,PS）三类准线性MCS的概念模型和结构特征出发,根据追踪轨迹计算MCS的运动方向和MCS近似长轴两侧层状云和强对流云的面积占比,建立准线性MCS的分类算法。MCS的识别属于二分分类问题,以命中率（POD）、虚警率（FAR）、临界成功指数（CSI）和准确率（ACC）为评价指标,综合对比各项指标发现DNN模型较SVM、RF和XGBoost模型对MCS的识别效果更好。使用时、空重叠追踪法对DNN模型识别的MCS进行追踪,结合对两个追踪实例的分析,发现本研究所用的算法取得了很好的追踪结果,也进一步说明了深度学习方法识别MCS的准确性和优势。根据追踪轨迹计算某时刻MCS的运动方向,结合识别的层状云和强对流云的分布位置,准确实现了TS、LS和PS型准线性MCS的分类,为准线性MCS的生命史预测及其致灾天气特别是短时强降水的强度、位置和持续时间的客观预报提供了一种技术思路。 相似文献
16.
To meet the low warming targets proposed in the 2015 Paris Agreement,substantial reduction in carbon emissions is needed in the future.It is important to know how surface climates respond under low warming targets.The present study investigates the surface temperature changes under the low-forcing scenario of Representative Concentration Pathways(RCP2.6)and its updated version(Shared Socioeconomic Pathways,SSP1-2.6)by the Flexible Global Ocean-Atmosphere-Land System(FGOALS)models participating in phases 5 and 6 of the Coupled Model Intercomparison Project(CMIP5 and CMIP6,respectively).In both scenarios,radiative forcing(RF)first increases to a peak of 3 W m^?2 around 2045 and then decreases to 2.6 W m^?2 by 2100.Global mean surface air temperature rises in all FGOALS models when RF increases(RF increasing stage)and declines or holds nearly constant when RF decreases(RF decreasing stage).The surface temperature change is distinct in its sign and magnitude between the RF increasing and decreasing stages over the land,Arctic,North Atlantic subpolar region,and Southern Ocean.Besides,the regional surface temperature change pattern displays pronounced model-to-model spread during both the RF increasing and decreasing stages,mainly due to large intermodel differences in climatological surface temperature,ice-albedo feedback,natural variability,and Atlantic Meridional Overturning Circulation change.The pattern of tropical precipitation change is generally anchored by the spatial variations of relative surface temperature change(deviations from the tropical mean value)in the FGOALS models.Moreover,the projected changes in the updated FGOALS models are closer to the multi-model ensemble mean results than their predecessors,suggesting that there are noticeable improvements in the future projections of FGOALS models from CMIP5 to CMIP6. 相似文献
17.
清洁能源的开发利用已成为当前能源发展的重要途径。为了客观评价赤峰市太阳能资源的储量与开发潜力,利用赤峰市14个国家气象观测站1986—2015年的日照时数资料,采用GIS技术和气候学方法,分析了当地太阳能资源的储量和稳定程度。结果表明:赤峰市太阳能资源储量丰富,年总辐射量在5600.78~6262.45 MJ/m2,平均为6025.16 MJ/m2,属于太阳能资源很丰富区且非常稳定,但太阳能资源的空间差异非常显著,特别在西部和北部的多山地区表现尤为明显。基于地形的太阳能资源开发适宜性区划分析表明,次适宜开发的面积最高达41.4%,最适宜和次适宜开发的总面积占全市面积的76.8%。同时考虑开发建设成本及环境保护因素,适合太阳能开发建设的草地和裸地,在最适宜和次适宜开发利用类别中占比分别达26.4%和30.7%,因此,赤峰市太阳能资源开发利用潜力巨大。 相似文献
18.
In this paper, we present four model-based scenarios exploring the potential for resource efficiency for energy, land and phosphorus use, and implications for resource depletion, climate change and biodiversity. The scenarios explored include technological improvements as well as structural changes in production systems and lifestyle changes. Many of such changes have long lead times, requiring up front and timely investments in infrastructure, innovative incentive structures and education. For simulating the scenarios we applied the IMAGE modelling framework, with a time horizon until 2050.Our findings confirm a large potential for more efficient resource use: our (no new policies) baseline scenario shows a global increase, between 2010 and 2050, by 80% of primary energy use, 4% of arable land and 40% of phosphorus fertilisers. These numbers are reduced to +25% (primary energy), −9% (arable land) and +9% (phosphorus) in the global resource efficiency scenario. Baseline developments and resource efficiency opportunities vary strikingly among regions, resources and sectors. Phosphorus use, for example, is expected to increase most on croplands in developing countries, whereas the largest potential for phosphorus use efficiency lies in the livestock sector and urban sewage treatment in industrialised countries. Consequently, while resource efficiency resonates well as a general notion in policy thinking, concrete policies need to be region-specific, resource-specific and sector-specific.Efficiency efforts on one resource tend to contribute to efficient use of other resources and to benefit the environment. There are also trade-offs, however, and the synergies analysed do not make problem-specific policies redundant: in 2050, the global resource efficiency scenario presents higher phosphorus use and higher use of fossil fuels than in 2010; greenhouse gas emission targets are met by half; and biodiversity loss slows down but is not halted. Moreover, part of the efficiency gains in land and phosphorus use is sacrificed when this scenario is combined with ambitious climate policy, due to the substantial resource requirements for the deployment of bio-energy—albeit much less than in a scenario without more efficient resource use. 相似文献
19.
Amit G. Dhorde Mohammad Zarenistanak R. H. Kripalani B. Preethi 《Meteorology and Atmospheric Physics》2014,124(3-4):205-216
Analysis of trends and projection of precipitation are of significance for the future development and management of water resource in southwest Iran. This research has been divided into two parts. The first part consists of an analysis of the precipitation over 50 stations in the study region for the period 1950–2007. The trends in this parameter were detected by linear regression and significance was tested by t test. Mann–Kendall rank test was also employed to confirm the results. The second part of the research involved future projection of precipitation based on four models. The models used were Centre National de Recherches Meteorologiques (CNRM), European Center Hamburg Model (ECHAM), Model for Interdisciplinary Research on Climate (MIROCH) and United Kingdom Meteorological Office (UKMOC). Precipitation projections were done under B1 and A1B emissions scenarios. The results of precipitation series indicated that most stations showed insignificant trend in annual and seasonal series. The highest numbers of stations with significant trends occurred in winter while no significant trends were detected by statistical tests in summer precipitation. No decreasing significant trends were detected by statistical tests in annual and seasonal precipitation series. The result of projections showed that precipitation may decrease according to majority of the models under both scenarios but the decrease may not be large, except according to MIROCH model. Autumn precipitation may increase with higher rates than other seasons at the end of this century. 相似文献
20.
利用华南地区观测站1981—2010年的总曝辐量数据及日照时数数据,对该地区太阳能资源的丰富程度和稳定程度进行评估。结果表明:华南地区总体太阳能资源价值呈现为海南最高,广东其次,广西最低。华南地区最佳倾斜面太阳总辐射年曝辐量为1291 kW·h·m-2,比水平面高3%,总体处于资源丰富等级以上。稳定度评估结果表明:华南地区大部分面积处于稳定等级以上,其中海南2/3以上的面积处于很稳定的等级。结合地形数据和土地覆盖数据,分别以90 m×90 m和1 km×1 km的分辨率对华南地区太阳能资源的开发适宜性进行区划和可利用潜力进行分析,结果显示:90 m×90 m分辨率下可开发利用的Ⅰ,Ⅱ,Ⅲ类地区的面积占华南地区总面积的80%以上,但其中裸地和灌木、草地仅占总面积的13.9%,而耕地和林地所占面积比例超过60%。受数据分辨率及获取年代差异的影响,1 km×1 km分辨率下太阳能开发适宜性区划结果与90 m×90 m分辨率的结果不尽相同,从而导致开发潜力也存在较大差异,在制定太阳能开发规划时应根据实际工程规模选择合理的数据。 相似文献