These data are associated with the paper being submitted entitled: Bayesian inference of tools for assessment of the physicochemical quality of a tropical lagoon. The data collection covered a 9-year period divided into three sets of years: 2002 - 2006; 2014 -2016; and 2021. All data were acquired from several comparable scientific studies using the same methods (AFNOR, 1997). The first two sets of data had approximately 16% missing data. The imputation of these missing data was performed using the non-parametric "missForest" algorithm for mixed type data. These data sets come from our field work and the field work that led to the following publications: Gnohossou, 2006; Odountan et al., 2019, Zandagba et al., 2016a, 2016b) . A total of 20 parameters were monitored, among which the following 17 physico-chemical parameters were selected: Water temperature (Temp), transparency (Trans), turbidity (Turb), conductivity (Cond), salinity (Sal), pH, dissolved oxygen (DO), BOD, COD, Kjeldahl nitrogen (TKN), ammonium, nitrates, nitrites, dry organic matter (DM), orthophosphates (Ortho_P), total phosphorus (TP), suspended solids (SM). The geographical distribution of the sampling points is made in order to cover the whole Nokou�� lagoon complex. In total, 20 sampling points were monitored. The parameters were measured according to the four seasons of the year and/or according to the succession of high water, low water, high water and low water transitions. Nine driving forces described as factors likely to induce pressure were retained to explain the physico-chemical characteristics of the Nokou��. The data from the land use maps obtained were used to establish the data related to the land use variables (OCA, OCU and OCF). To these 03 land use variables were added 04 other variables capturing the distances between the monitored stations and the 04 tributaries of the Nokou�� (So, MR, DR, TC). The present observations of these 07 variables could be improved with time depending on the availability of more accurate maps. As natural forcing variables, we have the sampling years, the seasons (SWS: short wet season or flood period; SDS: short dry season; LWS: long wet season; LDS: long dry season), the mean monthly water level (MAWL) and the mean wind speed (AWS). These natural forcing variables are important in the context of Nokou��... **Minor modifications** -Zipped data files - Addition of the validation dataset (data_validation.csv)

*lac_Nokoue_raw : Real data ; *lac_Nokoue : Dataset completed after imputation from the missForest algorithm and used in the context of the article being submitted