Search

ABSTRACTThis study evaluated historical land-cover states in order to identify potential land-use transition regimes leading to land degradation. Landsat satellite datasets were used to characterize land-cover states for 1986–2017 period. The multinomial probability distribution was used to establish sample size for training and accuracy assessment. Using a hybrid image classification approach, individual satellite images were initially clustered using the ISODATA technique, and spectral classes later transformed posteriori into respective thematic classes. Maximum Likelihood Function was subsequently used to assign pixels into classes with highest probability. Approximately 12% of mixed forest declined, while cropland increased by 30% between 1995–2008.

Long short‐term memory (LSTM) networks offer unprecedented accuracy for prediction in ungauged basins. We trained and tested several LSTMs on 531 basins from the CAMELS data set using k‐fold validation, so that predictions were made in basins that supplied no training data. The training and test data set included ∼30 years of daily rainfall‐runoff data from catchments in the United States ranging in size from 4 to 2,000 km2with aridity index from 0.22 to 5.20, and including 12 of the 13 IGPB vegetated land cover classifications. This effectively “ungauged” model was benchmarked over a 15‐year validation period against the Sacramento Soil Moisture Accounting (SAC‐SMA) model and also against the NOAA National Water Model reanalysis. SAC‐SMA was calibrated separately for each basin using 15 years of daily data. The out‐of‐sample LSTM had higher median Nash‐Sutcliffe Efficiencies across the 531 basins (0.69) than either the calibrated SAC‐SMA (0.64) or the National Water Model (0.58). This indicates that there is (typically) sufficient information in available catchment attributes data about similarities and differences between catchment‐level rainfall‐runoff behaviors to provide out‐of‐sample simulations that are generally more accurate than current models under ideal (i.e., calibrated) conditions. We found evidence that adding physical constraints to the LSTM models might improve simulations, which we suggest motivates future research related to physics‐guided machine learning. Overall accuracy of LSTMs in ungauged basins is comparable to standard hydrology models in gauged basinsThere is sufficient information in catchment characteristics data to differentiate between catchment‐specific rainfall‐runoff behaviors

Parameter estimation is one of the most challenging tasks in large‐scale distributed modeling, because of the high dimensionality of the parameter space. Relating model parameters to catchment/landscape characteristics reduces the number of parameters, enhances physical realism, and allows the transfer of hydrological model parameters in time and space. This study presents the first large‐scale application of automatic parameter transfer function (TF) estimation for a complex hydrological model. The Function Space Optimization (FSO) method can automatically estimate TF structures and coefficients for distributed models. We apply FSO to the mesoscale Hydrologic Model (mHM, mhm-ufz.org), which is the only available distributed model that includes a priori defined TFs for all its parameters. FSO is used to estimate new TFs for the parameters “saturated hydraulic conductivity” and “field capacity,” which both influence a range of hydrological processes. The setup of mHM from a previous study serves as a benchmark. The estimated TFs resulted in predictions in 222 validation basins with a median NSE of 0.68, showing that even with 5 years of calibration data, high performance in ungauged basins can be achieved. The performance is similar to the benchmark results, showing that the automatic TFs can achieve comparable results to TFs that were developed over years using expert knowledge. In summary, the findings present a step toward automatic TF estimation of model parameters for distributed models. This study shows the performance of automatic transfer function (TF) estimation with the Function Space Optimization (FSO) methodWe show that FSO is able to estimate TFs that perform similar to the mesoscale Hydrologic Model TFs in an ungauged settingThis study represents a step toward automatic TF estimation for physically interpretable model parameters This study shows the performance of automatic transfer function (TF) estimation with the Function Space Optimization (FSO) method We show that FSO is able to estimate TFs that perform similar to the mesoscale Hydrologic Model TFs in an ungauged setting This study represents a step toward automatic TF estimation for physically interpretable model parameters