Spatio-temporal interpolation of climatic variables over large region of complex terrain using neural networks

Antonić, Oleg; Križan, Josip; Marki, Antun; Bukovec, Dragan

doi:10.1016/s0304-3800(00)00406-3

Cited by 81 publications

(48 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Generally, only elevation is included as an auxiliary variable when compiling ET o maps via geostatistical techniques such as co-kriging (Martínez-Cob and Cuenca, 1992;Martínez-Cob, 1996;Noshadi and Sepaskhah, 2005;Mardikis et al, 2005) or neural networks (Antonic et al, 2001). These studies have shown that the incorporation of elevation data notably improves the performance of the estimates; however, in the present paper we have demonstrated the even greater potential of regressionbased interpolation and GIS in mapping ET o .…”

Section: Discussionmentioning

confidence: 63%

See 1 more Smart Citation

Comparison of different procedures to map reference evapotranspiration using geographical information systems and regression‐based techniques

Vicente‐Serrano

Lanjeri

López‐Moreno

2007

Intl Journal of Climatology

View full text Add to dashboard Cite

Abstract:This paper compares different procedures for mapping reference evapotranspiration (ET o ) by means of regression-based techniques and geographical information systems (GIS). ET o is calculated following the method of Hargreaves (HG) from a dense database of meteorological stations in the northernmost semi-arid region of Europe, the Ebro valley. The HG method requires the calculation of estimates of extraterrestrial radiation (R a ). We calculated this parameter using two approaches: (1) the common approach that assumes a planar surface and determines the parameter as a function of latitude and (2) using a digital terrain model (DTM) and GIS modelling. The maps were made on a monthly basis using both approaches. We also compared possible propagations of errors in the map calculations for maps derived from modelled layers of maximum and minimum temperatures with those modelled using previously determined local ET o calculations. We demonstrate that calculations of R a from a DTM and GIS modelling provide a more realistic spatial distribution of ET o than those derived by only considering latitude. It is also preferable to model in advance the variables involved in the calculation of ET o (temperature and R a ) and to subsequently calculate ET o by means of layer algebra in the GIS rather than directly model the local ET o calculations. The obtained maps are useful for the purposes of agriculture and ecological and water resources management in the study area.

show abstract

Section: Discussionmentioning

confidence: 63%

“…Martínez-Cob, 1996;Antonic et al, 2001;Ray and Dadhwal, 2001;Dalezios et al, 2002;Häntzschel et al, 2005;Mardikis et al, 2005). Most of the procedures are based on local estimates of ET o from meteorological data collected at available weather stations.…”

Section: S M Vicente-serrano S Lanjeri and J I López-morenomentioning

confidence: 99%

Comparison of different procedures to map reference evapotranspiration using geographical information systems and regression‐based techniques

Vicente‐Serrano

Lanjeri

López‐Moreno

2007

Intl Journal of Climatology

View full text Add to dashboard Cite

show abstract

“…We must stress that we have implemented standard procedures for training the NN in order to provide a more direct way to compare our work to other proposals (e.g. Antonic et al, 2001). However, we believe that the richness and the complexity of the spatial problem requires more sophisticated, ad hoc, training procedures in order to achieve better performance.…”

Section: Resultsmentioning

confidence: 99%

“…Rather then using the UK with a trend function modelled via a set of covariates, some authors (e.g. Agnew and Palutikof, 2000;Ninyerola et al, 2000;Antonic et al, 2001) have proposed a simpler approach based on RK, i.e. 'kriging after de-trending' where the trend function and estimated residuals are modelled separately.…”

Section: Krigingmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of interpolation methods for mapping climatic and bioclimatic variables at regional scale

Attorre

Alfó

Sanctis

et al. 2007

Intl Journal of Climatology

158

View full text Add to dashboard Cite

Abstract:Climatic data and bioclimatic indexes have been used to study plants, animals and ecosystem distribution. GIS-based maps of climatic and bioclimatic data can be obtained by interpolating values observed at measurement stations. Since no single method can be considered as optimal for all observed regions, a major task is to propose comparisons between results obtained using different methods applied to the same data set of climate variables. We compared three methods that have been proved to be useful at regional scale: 1 -a local interpolation method based on de-trended inverse distance weighting (D-IDW), 2 -universal kriging (i.e. simple kriging with trend function defined on the basis of a set of covariates) which is optimal (i.e. BLUP, best linear unbiased predictor) if spatial association is present, 3 -multilayer neural networks trained with backpropagation (representing a complex nonlinear fitting). Long-term (1955Long-term ( -1990 average monthly data were obtained from weather stations measuring precipitation (201 sites) and temperature (102 sites). We analysed twelve climatic variables (temperature and precipitation) and nine bioclimatic indexes. Terrain variables and geographical location have been used as predictors of the climate variables: longitude, latitude, elevation, aspect, slope, continentality and estimated solar radiation. Based on the root mean square errors from cross-validation tests, we ranked the best method for each variable data set. Universal kriging with external drift obtained the best performances for seventeen variables of the twenty-one analysed, neural network interpolator has proven to be more efficient for three variables and D-IDW for only one. Based on these results, we used the universal kriging estimates to produce the climatic and bioclimatic maps aimed at defining the bioclimatic envelope of species.

show abstract

New gridded daily climatology of Finland: Permutation‐based uncertainty estimates and temporal trends in climate

2016

View full text Add to dashboard Cite

Long‐term time series of key climate variables with a relevant spatiotemporal resolution are essential for environmental science. Moreover, such spatially continuous data, based on weather observations, are commonly used in, e.g., downscaling and bias correcting of climate model simulations. Here we conducted a comprehensive spatial interpolation scheme where seven climate variables (daily mean, maximum, and minimum surface air temperatures, daily precipitation sum, relative humidity, sea level air pressure, and snow depth) were interpolated over Finland at the spatial resolution of 10 × 10 km2. More precisely, (1) we produced daily gridded time series (FMI_ClimGrid) of the variables covering the period of 1961–2010, with a special focus on evaluation and permutation‐based uncertainty estimates, and (2) we investigated temporal trends in the climate variables based on the gridded data. National climate station observations were supplemented by records from the surrounding countries, and kriging interpolation was applied to account for topography and water bodies. For daily precipitation sum and snow depth, a two‐stage interpolation with a binary classifier was deployed for an accurate delineation of areas with no precipitation or snow. A robust cross‐validation indicated a good agreement between the observed and interpolated values especially for the temperature variables and air pressure, although the effect of seasons was evident. Permutation‐based analysis suggested increased uncertainty toward northern areas, thus identifying regions with suboptimal station density. Finally, several variables had a statistically significant trend indicating a clear but locally varying signal of climate change during the last five decades.

show abstract

Spatio-temporal interpolation of climatic variables over large region of complex terrain using neural networks

Cited by 81 publications

References 15 publications

Comparison of different procedures to map reference evapotranspiration using geographical information systems and regression‐based techniques

Comparison of different procedures to map reference evapotranspiration using geographical information systems and regression‐based techniques

Comparison of interpolation methods for mapping climatic and bioclimatic variables at regional scale

New gridded daily climatology of Finland: Permutation‐based uncertainty estimates and temporal trends in climate

Contact Info

Product

Resources

About