A solution to the inverse problem in groundwater is presented with a g
eostatistical framework, using Kalman filtering and a nonlinear gradie
nt-based search technique. The Kalman filtering recursions are based o
n a newly developed and linear state-space equation that relates aquif
er head perturbations to stochastic perturbations of log-aquifer prope
rties and effective recharge. The Davidon-Fletcher-Powell (DFP) search
algorithm is used to identify the mean and the variance of log-aquife
r transmissivity and storativity, by minimizing the joint negative log
-likelihood function of the innovations (prediction errors). Applicati
on to a numerical experiment indicates that the methodology performs w
ell for log-transmissivity integral scale smaller than aquifer dimensi
ons. The results underline the need for conditioning on point measurem
ents of transmissivity and storativity, if the objective is to estimat
e the variance parameters. While head measurements are instrumental fo
r estimating the geometric means (large-scale parameters), they, howev
er, may not be sufficient for inferring the variance of log-aquifer pr
operties (small-scale parameters).