In mountainous rural settlements facing the threat of geohazards,local adaptation is a self-organizing process influenced by individual and group behaviors.Encouraging a wide range of local populations to embrace geoh...In mountainous rural settlements facing the threat of geohazards,local adaptation is a self-organizing process influenced by individual and group behaviors.Encouraging a wide range of local populations to embrace geohazard adaptation strategies emerges as a potent means of mitigating disaster risks.The purpose of this study was to investigate whether neighbors influence individuals'adaptation decisions,as well as to unravel the mechanisms through which neighborhood effects exert their influence.We employed a spatial Durbin model and a series of robustness checks to confirm the results.The dataset used in this research came from a face-to-face survey involving 516 respondents residing in 32 rural settlements highly susceptible to geohazards.Our empirical results reveal that neighborhood effects are an important determinant of adaptation to geohazards.That is,a farmer's adaptation decision is influenced by the adaptation choices of his/her neighbors.Furthermore,when neighbors adopt adaptation strategies,the focal individuals may also want to adapt,both because they learn from their neighbors'choices(social learning)and because they tend to abide by the majority's choice(social norms).Incorporating neighborhood effects into geohazard adaptation studies offers a new perspective for promoting disaster risk reduction decision making.展开更多
Geographical information systems(GIS)are essential tools for mineral prospectivity modeling(MPM).Three-dimensional(3D)MPM is able to learn the association between geological evidence and mineralization in shallow zone...Geographical information systems(GIS)are essential tools for mineral prospectivity modeling(MPM).Three-dimensional(3D)MPM is able to learn the association between geological evidence and mineralization in shallow zones and thereby build a prospectivity model for deep zones,making it a desirable technique to target deep-seated orebodies.However,existing 3D MPM methods directly generalize the model learned in shallow zones to the deep zones without attention to model transferability caused by the different metallogenic mechanisms between the two zones.In this study,we aim to robustly transfer the prospectivity model learned from shallow zones to deep zones.We cast the 3D MPM as a domain adaptation problem,which is an important realm of transfer learning.Because the metallogenic mechanism can be closely associated with spatial locations,we specifically focus on domain adaption concerning the spatial locations that are ignored by conventional domain adaptation methods.To measure the spatial-associated domain discrepancy,we propose a novel spatial-associated maximum mean discrepancy(SAMMD),which compares the joint distributions of features and spatial locations across domains.Based on the SAMMD criterion,a deep neural network,referred to as the spatial-associated domain adaptation network,is devised to learn cross-domain but mineralization-indicative features for building prospectivity model that is transferable to deep zones.A case study of the world-class Sanshandao gold deposit,in eastern China,was carried out to validate the effectiveness of the proposed methods.The results show that compared with other leading MPM methods and other domain adaption variants,the proposed method has superior prediction accuracy and targeting efficiency,demonstrating the effectiveness and robustness of the proposed method in targeting deep-seated orebodies in areas with different metallogenic mechanisms and no labeled data.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.42071222)the Sichuan Science and Technology Program(No.2022JDJQ0015)+1 种基金the Fundamental Research Funds for the Central Universities(No.2023CDSKXYGG006)the Tianfu Qingcheng Program(No.ZX20220027)。
文摘In mountainous rural settlements facing the threat of geohazards,local adaptation is a self-organizing process influenced by individual and group behaviors.Encouraging a wide range of local populations to embrace geohazard adaptation strategies emerges as a potent means of mitigating disaster risks.The purpose of this study was to investigate whether neighbors influence individuals'adaptation decisions,as well as to unravel the mechanisms through which neighborhood effects exert their influence.We employed a spatial Durbin model and a series of robustness checks to confirm the results.The dataset used in this research came from a face-to-face survey involving 516 respondents residing in 32 rural settlements highly susceptible to geohazards.Our empirical results reveal that neighborhood effects are an important determinant of adaptation to geohazards.That is,a farmer's adaptation decision is influenced by the adaptation choices of his/her neighbors.Furthermore,when neighbors adopt adaptation strategies,the focal individuals may also want to adapt,both because they learn from their neighbors'choices(social learning)and because they tend to abide by the majority's choice(social norms).Incorporating neighborhood effects into geohazard adaptation studies offers a new perspective for promoting disaster risk reduction decision making.
基金funded by the National Natural Science Foundation of China(Nos.41972309,42272344,42030809,42072325,72088101)National Key R&D Program of China(No.2019YFC1805905).
文摘Geographical information systems(GIS)are essential tools for mineral prospectivity modeling(MPM).Three-dimensional(3D)MPM is able to learn the association between geological evidence and mineralization in shallow zones and thereby build a prospectivity model for deep zones,making it a desirable technique to target deep-seated orebodies.However,existing 3D MPM methods directly generalize the model learned in shallow zones to the deep zones without attention to model transferability caused by the different metallogenic mechanisms between the two zones.In this study,we aim to robustly transfer the prospectivity model learned from shallow zones to deep zones.We cast the 3D MPM as a domain adaptation problem,which is an important realm of transfer learning.Because the metallogenic mechanism can be closely associated with spatial locations,we specifically focus on domain adaption concerning the spatial locations that are ignored by conventional domain adaptation methods.To measure the spatial-associated domain discrepancy,we propose a novel spatial-associated maximum mean discrepancy(SAMMD),which compares the joint distributions of features and spatial locations across domains.Based on the SAMMD criterion,a deep neural network,referred to as the spatial-associated domain adaptation network,is devised to learn cross-domain but mineralization-indicative features for building prospectivity model that is transferable to deep zones.A case study of the world-class Sanshandao gold deposit,in eastern China,was carried out to validate the effectiveness of the proposed methods.The results show that compared with other leading MPM methods and other domain adaption variants,the proposed method has superior prediction accuracy and targeting efficiency,demonstrating the effectiveness and robustness of the proposed method in targeting deep-seated orebodies in areas with different metallogenic mechanisms and no labeled data.
