인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
개인구독
소속 기관이 없으신 경우, 개인 정기구독을 하시면 저렴하게
논문을 무제한 열람 이용할 수 있어요.
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
In this paper, a new approach for the improvement of accuracy in DEMs (Digital Elevation Models) was proposed. While algorithms such as bilinear, bicubic, Kriging, and the HNN (Hopfield neural network) model can enhance the accuracy of DEMs, especially those derived from global data sources such as SRTM, ASTER, etc., the inclusion of additional elevation data can further improve the accuracy of the DEM. In this paper, a newly proposed resolution enhancing HNN model with the incorporation of elevation adjustment functions and variations in constraint conditions was developed and evaluated. The evaluation of the model was implemented in Cao Bang using SRTM 30m DEM data in a 1650m × 1344m area, with 130 elevation points used for accuracy enhancement and 64 points used for evaluation. The test results show an increase in accuracy of up to 40% in terms of both roots mean square error and mean absolute error when the additional elevation points were used. It has also been discovered that a zoom factor of 4 provides the best optimization in terms of balancing accuracy and computing cost for the newly proposed HNN downscaling algorithm. The results indicate that the model has the potential to be applied in practice to enhance the accuracy of DEMs, especially global DEMs after additional evaluation.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-24-02-088339971