Abstract
A new approach to characterise geographical areas with a drought risk index (DRI) is suggested, by applying an artificial neural network (ANN) classifier to bioclimatic time series for which operational temporal units (OtUs) are defined. A climatic database, corresponding to a grid of 8 km × 8 km cells covering the Italian peninsula, was considered. Each cell is described by the time series of seven variables recorded from 1989 to 2000. Sixteen cells were selected according to land cover homogeneity and completeness of the time series data. The periodic components of the time series were calculated by means of the fast Fourier transform (FFT) method. Temporal units corresponding to the period of the sinusoidal functions most related to the data were used as OtUs. The ANN for each OtU calculates a DRI value ranging between −1 and 1. The value is interpretable as the proximity of the OtUs to one of two situations corresponding to minimum and maximum drought risk, respectively. The former set (DRI = −1) is represented by an ideal OtU with minimum values of temperatures and evapo-transpiration, and maximum values of rainfall, normalised difference vegetation index (NDVI) and soil water content. The second set (DRI = 1) is represented by the reciprocal OtU to the former one. The classification of the cells based on DRI time profiles showed that, at the scale used in this work, DRI has no dependence on land cover class, but is related to the location of the cells. The methodology was integrated with GIS (geographic information system) software, and used to show the geographic pattern of DRI in a given area at different periods.
Similar content being viewed by others
References
AA. VV. (1992) Agricoltura e telerilevamento: Statistiche agricole per il 1992. Monografia del Ministero dell’Agricoltura e Foreste (MAF), Roma, Italy
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Brigham EO (1974) The fast Fourier transform. Prentice-Hall, Englewood Cliffs
Carlson TN, Ripley DA (1997) On the relation between NDVI, fractional vegetation cover, and leaf area index. Remote Sens Environ 62:241–252
Cihlar J, St-Laurent L, Dyer JA (1991) Relation between the normalized difference vegetation index and ecological variables. Remote Sens Environ 35:279–298
Crovello TJ (1981) Quantitative biogeography: an overview. Taxon 30:563–575
Feoli E, Zuccarello V (1996) Spatial pattern of ecological processes: the role of similarity in GIS applications for landscape analysis. In: Fisher M, Scholten H, Unwin D (eds) Spatial analytical perspectives on GIS. Taylor and Francis, London, pp 175–185
Feoli E, Giacomich P, Mignozzi K, Oztürk M, Scimone M (2003) Monitoring desertification risk with an index integrating climatic and remotely-sensed data: an example from the coastal area of Turkey. Manage Environ Qual 14:10–21
Gamo M (1999) Classification of arid regions by climate and vegetation. J Arid Land Studies 9:17–26
Gopal S, Woodcock CE, Strahler AH (1999) Fuzzy neural network classification of global land cover from a 1° AVHRR data set. Remote Sens Environ 67:230–243
Goward SN, Markhan B, Dye DG, Dulaney W, Yang J (1991) Normalized difference vegetation index measurements from the advanced very high resolution radiometer. Remote Sens Environ 35:257–277
Haykin S (1994) Neural networks—a comprehensive foundation. Macmillan, New York
Henderson CE (2000) Predicting aflatoxin contamination in peanuts: a genetic algorithm/neural network approach. Appl Intell 12:183–192
Hoptroff R (1993) The principles and practice of times series forecasting and business modelling using neural nets. Neural Comput Appl 1:59–66
Karnieli A (2000) Drought monitoring in the Negev desert using NOAA/AVHRR imagery. Proceeding of Agroenvironment 2000, II International symposium on New Technologies for Environment Monitoring and Agro-Applications, Tekirdag, Turkey
Keetch JJ, Byram GM (1968) A drought index for forest fire control. Research Paper 38, US Dept of Agriculture, Washington
Kuo C, Reitsch A (1995) Neural networks vs conventional methods of forecasting. J Business Forecast Method Syst 14:17–22
Kwak NK, Changwon L (1997) Neural network application to classification of health status of HIV/AIDS patients. J Med Syst 21:87–97
Laepes A, Farben R (1987) Nonlinear signal processing using neural networks: prediction and system modelling. Tech Rep, Los Alamos National Laboratory, Los Alamos, New Mexico
Lek S, Guégan JF (1999) Artificial neural networks as a tool in ecological modelling, an introduction. Ecological Modelling 120(2–3):65–73
McKee TB, Doesken NJ, Kleist J (1993) The relationship of drought frequency and duration to time scales. Proceedings of the VIII Conference on Applied Climatology, Boston. Am Meteorol Soc:179–184
Mitchell A (ed) (1999) The ESRI guide to GIS analysis. ESRI Press, Redlands, CA
Moshiri S (1999) Static, dynamic, and hybrid neural networks in forecasting inflation. Comput Econ 14:219–235
Palmer WC (1965) Meteorological Drought. Research Paper 45, US Dept of Commerce, Washington
Podani J (2001) SYN-TAX 2000. Computer programs for data analysis in ecology and systematics. User’s manual. Scientia, Budapest
Ricotta C, Avena G, De Palma A (1999) Mapping and monitoring net primary productivity with AVHRR NDVI time-series: statistical equivalence of cumulative vegetation indices. J Photogramm Remote Sens 54:325–331
Ruimy A, Saugier B, Dedieu G (1994) Methodology for the estimation of terrestrial net primary production from remotely sensed data. J Geophys Res 99:5263–5283
Rumelhart DE, McClellan JL (1986) Parallel distributed processing: exploration in the microstructure of cognition. Vol 1: foundations. MIT Press, Cambridge
Svoboda M, LeComte D, Hayes M, Heim R, Gleason K, Angel J, Rippry B, Tinker R, Palecki M, Stooksbury D, Miskus D, Stephens S (2002) The drought monitor. Bull Am Meteor Soc 83:1181–1190 DOI 10.1175/1520-0477(2002)083
Taddei R (1997) Maximum value interpolated MVI: a maximum value composite method improvement in vegetation index profile analysis. Int J Remote Sens 18:2365–2370
Tadesse T, Wilhite DA, Harms SK, Hayes MJ, Goddard S (2004) Drought monitoring using data mining techniques: a case study for Nebraska, USA. Nat Hazards 33:137–159
Thornthwaite CW (1948) An approach towards a rational classification of climate. Geogr Rev 38:55–94
Tucker CJ (1979) Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ 8:127–150
Vertovec M, Saçkali S, Oztürk M, Salleo S, Giacomich P, Feoli E, Nardini A (2001) Diagnosing plant water status as a tool for quantifying water stress on a regional basis in Mediterranean drylands. Ann For Sci 58:113–125
Wasserman P (ed) (1989) Neural computing: theory and practice. Van Nostrand Reinhold, New York
White H (ed) (1992) Artificial neural networks: approximation and learning theory. Blackwell, Oxford
Wilhite DA (1992) Drought. Encycl Earth Syst Sci 2:81–92
Wilhite DA (2000) Reducing societal vulnerability to drought. In: Wilhite DA (ed) Drought: a global assessment. Routledge, London, pp 295–298
Wu H, Wilhite DA (2004) An operational agricultural drought risk assessment model for Nebraska, USA. Natural Hazards 33:1–21
Acknowledgments
This study is part of the “CLIMAGRI–Cambiamenti Climatici e Agricoltura” Research Project, and has been funded by the Italian Ministry of Forests and Agriculture Policy. This work was completed within the framework of “Centro di Eccellenza per la Ricerca in Telegeomatica e Informazione Spaziale-Università degli studi di Trieste”.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Incerti, G., Feoli, E., Salvati, L. et al. Analysis of bioclimatic time series and their neural network-based classification to characterise drought risk patterns in South Italy. Int J Biometeorol 51, 253–263 (2007). https://doi.org/10.1007/s00484-006-0071-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00484-006-0071-6