LANDSAT IMAGE AND SAMPLE DESIGN FOR WATER RESERVOIRS (RAPEL DAM CENTRAL CHILE) LEONARDO LAVANDEROS, M. EUGENIA POZO, CARLOS PATTILLO and HERN,~N MIRANDA Unidad de Sistemas de Informacidn Geogrdfica y Percepcidn Remota, Depto. de Ciencias Ecoldgicas, Facultad de Ciencias, Universidad de Chile, casilla 563, Santiago, Chile Centro de Estudios Espaciales, Facultad de Ciencias Ffsicas y Matemdticas, Universidad de Chile, Santiago, Chile. (Received August 1988) Abstract, Spatial heterogeneity of the Rapel reservoir surface waters is analyzed through Landsat images. The image digital counts are used with the aim or developing an aprioristic quantitative sample design. Natural horizontal stratification of the Rapel Reservoir (Central Chile) is produced mainly by suspended solids. The spatial heterogeneity conditions of the reservoir for the Spring 86 - Summer 87 period were determined by qualitative analysis and image processing of the MSS Landsat, bands 1 and 3. The space-time variations of the different observed strata obtained with muItitemporal image analysis. A random stratified sample design (r.s.s.d) was developed, based on the digital counts statisticai analysis. Strata population size as well as the average, variance and sampling size of the digital counts were obtained by the r.s.s.d method. Stratification determined by analysis of satellite images were later correlated with ground data. Though the stratification of the reservoir is constant over time, the shape and size of the strata varys. Introduction To be meaningful, the sampling design for evaluation of aquatic resources must incorporate the spatial configuration of the system elements. The multispectral information of the Landsat image has been shown to be a very useful tool in monitoring processes of environmental phenomena related to water quality in natural lakes and reservoirs. Several authors (Verdin, 1985; Khorram et al., 1985; Lindell et al., 1986; Bartholdy and Folving, 1986) have succeeded in designing maps of water quality by means of the development of empirical equations for reflectance bands 1, 2, and 3 of the MSS Landsat and for variables such as: biomass (chlorophyll-a), transparency associated Secchi disk and suspended solids derived from field measurement. In most cases the researcher lacks the basic information about the spatial temporal variability of the most common parameters. One of the possible consequences of this difficulty is that the distribution and size of samples in the system studied are not always the most appropriate. In general, the field measurements design is a random simple sampling design (r.s.s.d) using the morphometric features of the water body. One unexplored possibility of the Landsat information applied to the study of lakes and reservoirs, is the use of the image digital counts in such a way that through the analysis of the variability of the sets of the digital values of the images (Landsat) Environmental Monitoring and Assessment 14: 9-22, 1990. 9 1990 Kluwer Academic Publishers. Printed in the Netherlands.