인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
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
Climate change has had ongoing impacts, each of which brings with them challenges to the sustainability of soil health by way of its impact on agricultural productivity. Reliable methods for predicting and managing changes in soil properties in response to increasing temperature fluctuations, shifting precipitation patterns, and extreme weather events are needed, as these changes are occurring in the face of soil properties. To answer the problem of soil degradation under climate stress, this research develops and evaluates predictive models capable of predicting soil health indicators. For modeling the key soil parameters (pH, organic matter, and moisture content), the proposed system uses machine learning techniques, namely Linear Regression, Support Vector Machine (SVM), Neural Networks, etc. In terms of these methods, the Random Forest model proved to be the most accurate and robust one since it consistently performs well in predicting soil health under various climate scenarios. The model's capacity to have sophisticated and nonlinear relationships within the data and its high precision and recall rate makes it a perfect instrument for soil health management. This study's results provide evidence of the strength of the Random Forest model to produce actionable, sustainable soil management insights that can appropriately ameliorate the problems associated with climate change in agricultural systems. Just as important, such predictive tools have to be implemented to promote resilience in agricultural practices and to achieve long-term soil health.
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
