Differentiable parameterized learning (dPL) represents a cutting-edge advancement in synergizing process-based models (PBMs) and machine learning to improve both the model prediction and interpretability. However, dPL...
Differentiable parameterized learning (dPL) represents a cutting-edge advancement in synergizing process-based models (PBMs) and machine learning to improve both the model prediction and interpretability. However, dPL mainly focuses on refining parameters within a predefined process-based structure, which limits its performance and process understanding to the constraints of existing PBM frameworks. To address this limitation, we propose an extended framework: Differentiable Process and Parameter Learnings (dP2Ls). dP2Ls incorporate regionalized neural networks (NNs) to simultaneously improve both the modeling of process variables and parameter learnings. Within dP2Ls, the EXP-HYDRO model serves as a differentiable physical backbone, where the potential evapotranspiration (PET) process is modeled using a regionalized long short-term memory (LSTM), while the dPL strategy is independently applied to learning hydrological parameters. Experiments with runoff prediction in ungauged catchments across the contiguous United States revealed that: (1) The median Nash-Sutcliffe efficiency (NSE) of regionalized dP2Ls in ungauged catchments surpassed that of all models using NNs for either process learning or parameter learning and approached the LSTM model (the median NSE differs by only 0.021); (2) Regionalized dP2Ls enhanced the interpretability of some intermediate variables by jointly learning the process variables and parameters, resulting in the correlation coefficients of snowpack and ET fitting the estimation products increased by 0.022 and 0.026, respectively; (3) The embedded regionalized LSTM outputs more interpretable PET than EXP-HYDRO, demonstrating the capability of NNs to improve traditional process understanding. In summary, this study demonstrates the advantages of dP2Ls in regionalized modeling, overcoming the limitations of traditional process-based structures through flexible NN configurations, and providing a reliable pathway for the future in-depth diagno
People detection in 2D laser range data is widely used in many application, such as robotics, smart cities or regions, and intelligent driving. For most current methods on people detection based on a single laser rang...
详细信息
Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of...
详细信息
Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of green tide is presented from Landsat TM/ETM plus image which needs not the atmospheric correction. In order to achieve an automatic detection of green tide, a linear relationship（y =0.723 x＋0.504） between detection threshold y and subtraction x（x=λnir–λred） is found from the comparing Landsat TM/ETM plus image with the field *** this relationship, green tide patches can be detected automatically from Landsat TM/ETM plus *** there is brightness difference between different regions in an image, the image will be divided into a plurality of windows（sub-images） with a same size firstly, and then each window will be detected using an adaptive detection threshold determined according to the discovered linear relationship. It is found that big errors will appear in some windows, such as those covered by clouds seriously. To solve this problem, the moving step k of windows is proposed to be less than the window width n. Using this mechanism, most pixels will be detected[n/k]×[n/k] times except the boundary pixels, then every pixel will be assigned the final class（green tide or sea water） according to majority rule voting strategy. It can be seen from the experiments, the proposed detection method using multi-windows and their adaptive thresholds can detect green tide from Landsat TM/ETM plus image automatically. Meanwhile, it avoids the reliance on the accurate atmospheric correction.
暂无评论