Machine learning(ML)is becoming an ever more important tool in hydrologic modeling.Previous studies have shown the higher prediction accuracy of those ML models over traditional process-based ones.However,there is ano...Machine learning(ML)is becoming an ever more important tool in hydrologic modeling.Previous studies have shown the higher prediction accuracy of those ML models over traditional process-based ones.However,there is another advantage of ML which is its lower computational demand.This is important for the applications such as hydraulic soil erosion estimation over a large area and at a finer spatial scale.Using traditional models like Rangeland Hydrology and Erosion Model(RHEM)requires too much computation time and resources.In this study,we designed an Artificial Neural Network that is able to recreate the RHEM outputs(annual average runoff,soil loss,and sediment yield and not the daily storm event-based values)with high accuracy(Nash-Sutcliffe Efficiency≈1.0)and a very low computational time(13 billion times faster on average using a GPU).We ran the RHEM for more than a million synthetic scenarios and train the Emulator with them.We also,fine-tuned the trained Emulator with the RHEM runs of the real-world scenarios(more than 32,000)so the Emulator remains comprehensive while it works specifically accurately for the real-world cases.We also showed that the sensitivity of the Emulator to the input variables is similar to the RHEM and it can effectively capture the changes in the RHEM outputs when an input variable varies.Finally,the dynamic prediction behavior of the Emulator is statistically similar to the RHEM.展开更多
The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph.However,such finding is mostly restricted to the...The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph.However,such finding is mostly restricted to the collaborative filtering(CF)scenario,where the interaction contexts are not available.In this work,we extend the advantages of graph convolutions to context-aware recommender system(CARS,which represents a generic type of models that can handle various side information).We propose Graph Convolution Machine(GCM),an end-to-end framework that consists of three components:an encoder,graph convolution(GC)layers,and a decoder.The encoder projects users,items,and contexts into embedding vectors,which are passed to the GC layers that refine user and item embeddings with context-aware graph convolutions on the user-item graph.The decoder digests the refined embeddings to output the prediction score by considering the interactions among user,item,and context embeddings.We conduct experiments on three real-world datasets from Yelp and Amazon,validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS.展开更多
Numerical simulations have revolutionized material design.However,although simulations excel at mapping an input material to its output property,their direct application to inverse design has traditionally been limite...Numerical simulations have revolutionized material design.However,although simulations excel at mapping an input material to its output property,their direct application to inverse design has traditionally been limited by their high computing cost and lack of differentiability.Here,taking the example of the inverse design of a porous matrix featuring targeted sorption isotherm,we introduce a computational inverse design framework that addresses these challenges,by programming differentiable simulation on TensorFlow platform that leverages automated end-to-end differentiation.Thanks to its differentiability,the simulation is used to directly train a deep generative model,which outputs an optimal porous matrix based on an arbitrary input sorption isotherm curve.Importantly,this inverse design pipeline leverages the power of tensor processing units(TPU)—an emerging family of dedicated chips,which,although they are specialized in deep learning,are flexible enough for intensive scientific simulations.This approach holds promise to accelerate inverse materials design.展开更多
Reliably identifying synthesizable inorganic crystalline materials is an unsolved challenge required for realizing autonomous materials discovery.In this work,we develop a deep learning synthesizability model(SynthNN)...Reliably identifying synthesizable inorganic crystalline materials is an unsolved challenge required for realizing autonomous materials discovery.In this work,we develop a deep learning synthesizability model(SynthNN)that leverages the entire space of synthesized inorganic chemical compositions.By reformulating material discovery as a synthesizability classification task,SynthNN identifies synthesizable materials with 7×higher precision than with DFT-calculated formation energies.In a head-to-head material discovery comparison against 20 expert material scientists,SynthNN outperforms all experts,achieves 1.5×higher precision and completes the task five orders of magnitude faster than the best human expert.Remarkably,without any prior chemical knowledge,our experiments indicate that SynthNN learns the chemical principles of charge-balancing,chemical family relationships and ionicity,and utilizes these principles to generate synthesizability predictions.The development of SynthNN will allow for synthesizability constraints to be seamlessly integrated into computational material screening workflows to increase their reliability for identifying synthetically accessible materials.展开更多
It is our great pleasure to edit this special section of the Journal of Computer Science and Technology （JCST）. The database field has experienced a rapid growth with increasing of data. Therefore, novel technology ...It is our great pleasure to edit this special section of the Journal of Computer Science and Technology （JCST）. The database field has experienced a rapid growth with increasing of data. Therefore, novel technology for covering emerging databases such as network or graph analysis, spatial or temporal data analysis, search, recommendation, and data mining is required. The goal of the section is to provide state-of-the-art research issues, challenges, new technologies, and solutions of emerging databases. This section publishes seven interesting articles related to query processing, trajectory data reduction, botnet evolution, recommendation system, bielustering, and protein structure alignment. The articles are summarized as follows.展开更多
基金supported by the U.S.Department of Agriculture,Natural Resources Conservation Service,Conservation Effects Assessment Project(CEAP)Grazing Lands Component,under agreement number NR193A750007C002。
文摘Machine learning(ML)is becoming an ever more important tool in hydrologic modeling.Previous studies have shown the higher prediction accuracy of those ML models over traditional process-based ones.However,there is another advantage of ML which is its lower computational demand.This is important for the applications such as hydraulic soil erosion estimation over a large area and at a finer spatial scale.Using traditional models like Rangeland Hydrology and Erosion Model(RHEM)requires too much computation time and resources.In this study,we designed an Artificial Neural Network that is able to recreate the RHEM outputs(annual average runoff,soil loss,and sediment yield and not the daily storm event-based values)with high accuracy(Nash-Sutcliffe Efficiency≈1.0)and a very low computational time(13 billion times faster on average using a GPU).We ran the RHEM for more than a million synthetic scenarios and train the Emulator with them.We also,fine-tuned the trained Emulator with the RHEM runs of the real-world scenarios(more than 32,000)so the Emulator remains comprehensive while it works specifically accurately for the real-world cases.We also showed that the sensitivity of the Emulator to the input variables is similar to the RHEM and it can effectively capture the changes in the RHEM outputs when an input variable varies.Finally,the dynamic prediction behavior of the Emulator is statistically similar to the RHEM.
基金supported by the National Key Research and Development Program of China (2020AAA0106000)the National Natural Science Foundation of China (Grant Nos.61972372,U19A2079,62121002).
文摘The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph.However,such finding is mostly restricted to the collaborative filtering(CF)scenario,where the interaction contexts are not available.In this work,we extend the advantages of graph convolutions to context-aware recommender system(CARS,which represents a generic type of models that can handle various side information).We propose Graph Convolution Machine(GCM),an end-to-end framework that consists of three components:an encoder,graph convolution(GC)layers,and a decoder.The encoder projects users,items,and contexts into embedding vectors,which are passed to the GC layers that refine user and item embeddings with context-aware graph convolutions on the user-item graph.The decoder digests the refined embeddings to output the prediction score by considering the interactions among user,item,and context embeddings.We conduct experiments on three real-world datasets from Yelp and Amazon,validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS.
基金H.L.acknowledges funding from the Fundamental Research Funds for the Central Universities under the Grant No.YJ202271M.B.acknowledges the National Science Foundation under the Grant No.DMREF-1922167TPU computing time was provided by a grant allocation from Google’s TensorFlow Research Cloud(TFRC)program.
文摘Numerical simulations have revolutionized material design.However,although simulations excel at mapping an input material to its output property,their direct application to inverse design has traditionally been limited by their high computing cost and lack of differentiability.Here,taking the example of the inverse design of a porous matrix featuring targeted sorption isotherm,we introduce a computational inverse design framework that addresses these challenges,by programming differentiable simulation on TensorFlow platform that leverages automated end-to-end differentiation.Thanks to its differentiability,the simulation is used to directly train a deep generative model,which outputs an optimal porous matrix based on an arbitrary input sorption isotherm curve.Importantly,this inverse design pipeline leverages the power of tensor processing units(TPU)—an emerging family of dedicated chips,which,although they are specialized in deep learning,are flexible enough for intensive scientific simulations.This approach holds promise to accelerate inverse materials design.
基金This work was performed under the auspices of the U.S.Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.We would like to thank Prof.Tony Heinz for the original project inspiration and the human participants of the Synthesizability Quiz.
文摘Reliably identifying synthesizable inorganic crystalline materials is an unsolved challenge required for realizing autonomous materials discovery.In this work,we develop a deep learning synthesizability model(SynthNN)that leverages the entire space of synthesized inorganic chemical compositions.By reformulating material discovery as a synthesizability classification task,SynthNN identifies synthesizable materials with 7×higher precision than with DFT-calculated formation energies.In a head-to-head material discovery comparison against 20 expert material scientists,SynthNN outperforms all experts,achieves 1.5×higher precision and completes the task five orders of magnitude faster than the best human expert.Remarkably,without any prior chemical knowledge,our experiments indicate that SynthNN learns the chemical principles of charge-balancing,chemical family relationships and ionicity,and utilizes these principles to generate synthesizability predictions.The development of SynthNN will allow for synthesizability constraints to be seamlessly integrated into computational material screening workflows to increase their reliability for identifying synthetically accessible materials.
文摘It is our great pleasure to edit this special section of the Journal of Computer Science and Technology （JCST）. The database field has experienced a rapid growth with increasing of data. Therefore, novel technology for covering emerging databases such as network or graph analysis, spatial or temporal data analysis, search, recommendation, and data mining is required. The goal of the section is to provide state-of-the-art research issues, challenges, new technologies, and solutions of emerging databases. This section publishes seven interesting articles related to query processing, trajectory data reduction, botnet evolution, recommendation system, bielustering, and protein structure alignment. The articles are summarized as follows.
