Recent studies have demonstrated the importance of LUCC change with climate and ecosystem simulation,but the result could only be determined precisely if a high-resolution unde rlying land cover map is used.While the ...Recent studies have demonstrated the importance of LUCC change with climate and ecosystem simulation,but the result could only be determined precisely if a high-resolution unde rlying land cover map is used.While the efforts based satellites have provided a good baseline for presenl land cover,what the next advancement in the research about LUCC change required is the development of reconstruction of historical LUCC change,especially spatially-explicit histo rical dataset.Being different from other similar studies,this study is based on the analysis of historical land use patterns in the traditional cultivated reqion of China.Taking no account of the less important factors,altitude,slope and population patterns are selected as the major d rivers of reclamation in ancient China,and used to designthe HCGM(Histo rical Cropland Gridding Model,at a 60 km×60 km resolution),which is anempirical model for allocating the historical cropland inventory data spatially to grid cells ineach polltical unit.Then we use this model to reconstruct cropland distribution of the study area in 1 820,and verify the result by prefectural cropland data of 1 820,which is from thehistorical documents.The statistical analyzing result shows that the model can simulate the patterns of the cropland distribution in the historical pe riod in the traditional cultivated region efficiently.展开更多
臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首...臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首先交互模块(IC)可以通过一系列的卷积操作来捕捉短期上下文信息,其次层融合模块(LF)可以融合不同层的空间信息来获得上一时刻丰富的空间信息,最后差分时空LSTM模块(DSTM)将捕捉到的时间信息和空间信息进行统一建模实现臭氧浓度预测。所构建模型分别与卷积LSTM网络(ConvLSTM)、预测循环神经网络(PredRNN)以及Memory in Memory网络(MIM)模型在河北省气象局提供的臭氧浓度数据上进行了对比分析,ST-IDN模型的平均绝对误差分别降低了19.836%、12.924%、7.506%。实验结果表明,所提出的模型能够提高臭氧浓度的预测精度。展开更多
基金Natiional Natural Science Foundation of China,No.40471007Innovation Knowledge Project of CAS,No.KZCX2-YW-315
文摘Recent studies have demonstrated the importance of LUCC change with climate and ecosystem simulation,but the result could only be determined precisely if a high-resolution unde rlying land cover map is used.While the efforts based satellites have provided a good baseline for presenl land cover,what the next advancement in the research about LUCC change required is the development of reconstruction of historical LUCC change,especially spatially-explicit histo rical dataset.Being different from other similar studies,this study is based on the analysis of historical land use patterns in the traditional cultivated reqion of China.Taking no account of the less important factors,altitude,slope and population patterns are selected as the major d rivers of reclamation in ancient China,and used to designthe HCGM(Histo rical Cropland Gridding Model,at a 60 km×60 km resolution),which is anempirical model for allocating the historical cropland inventory data spatially to grid cells ineach polltical unit.Then we use this model to reconstruct cropland distribution of the study area in 1 820,and verify the result by prefectural cropland data of 1 820,which is from thehistorical documents.The statistical analyzing result shows that the model can simulate the patterns of the cropland distribution in the historical pe riod in the traditional cultivated region efficiently.
基金partly supported by the Public Geological Survey Project(No.201011039)the National High Technology Research and Development Project of China(No.2007AA06Z134)the 111 Project under the Ministry of Education and the State Administration of Foreign Experts Affairs,China(No.B07011)
文摘臭氧浓度的预测对于大气环境治理、空气质量改善等起到了重要的作用。本文提出了一种交互差分时空LSTM网络预测模型(ST-IDN)来挖掘臭氧浓度历史数据的时间相关性和空间相关性,并成功将其应用到网格化臭氧浓度数据预测上。在该模型中,首先交互模块(IC)可以通过一系列的卷积操作来捕捉短期上下文信息,其次层融合模块(LF)可以融合不同层的空间信息来获得上一时刻丰富的空间信息,最后差分时空LSTM模块(DSTM)将捕捉到的时间信息和空间信息进行统一建模实现臭氧浓度预测。所构建模型分别与卷积LSTM网络(ConvLSTM)、预测循环神经网络(PredRNN)以及Memory in Memory网络(MIM)模型在河北省气象局提供的臭氧浓度数据上进行了对比分析,ST-IDN模型的平均绝对误差分别降低了19.836%、12.924%、7.506%。实验结果表明,所提出的模型能够提高臭氧浓度的预测精度。