• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Regional mapping of soil thickness predicted by machine learning techniques

Research Project

Project/Area Number 17K07865
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Forest science
Research InstitutionForest Research and Management Organization

Principal Investigator

Yamashita Naoyuki  国立研究開発法人森林研究・整備機構, 森林総合研究所, 主任研究員 等 (30537345)

Co-Investigator(Kenkyū-buntansha) 大貫 靖浩  国立研究開発法人森林研究・整備機構, 森林総合研究所, 地域研究監 (10353616)
Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Keywords土層厚 / 土壌深度 / 機械学習 / マッピング / 広域評価 / 山地・丘陵地 / デジタル土壌マッピング / 空間推定モデル / 空間推定 / 広域スケール / 山地小流域 / 広域マップ
Outline of Final Research Achievements

In Japan spatial information of soil thickness (soil depth) have not still developed. We predicted and mapped soil thickness in mountainous and hilly areas across Japan by machine learning regression. Legacy and new dataset of soil profile, boring survey and handy-dynamic-cone-penetrometer were used as training data. As a result, the accuracy of thickness of layer A, A+B and <=Nc5 layer (penetration resistance: Nc is <=5) were 0.25, 0.3 and 0.51 for R square and 11, 21 and 105 cm for RMSE, respectively. This map reproduced the spatial variation at the small watershed scale and regional variation on a national scale, which might be due to micro-topographic effect and tephra sedimentation. To improve the map accuracy of <=Nc5 thickness, the measurements on the top slopes of mountainous and hilly areas may be effective to determine the maximum soil thickness in the regions.

Academic Significance and Societal Importance of the Research Achievements

本研究により、全国スケールの土層厚予測マップが初めて報告された。土層厚は物質循環や水文モデルにおける大きな不確実性要因であるため、本研究の予測値を入力値として利用することにより、特に広域スケール適用時のモデル精度が大きく改善される可能性がある。また、本研究では予測誤差マップを同時に示しており、昨今のモデル研究で重要度が増している不確実性評価に対しての貢献も期待できる。土層厚マップの作成を通じた気候変動予測や防災リスクマップの高精度化による社会への波及効果は少なくないと考えられる。

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (8 results)

All 2020 2019 2018

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (7 results) (of which Int'l Joint Research: 2 results)

  • [Journal Article] Relationship between soil movement and changes of forest floor environments after clearing in the northernmost region of Okinawa Island2019

    • Author(s)
      大貫 靖浩、古堅 公、生沢 均、松浦 俊也、山下 尚之、新垣 拓也
    • Journal Title

      Japanese Journal of Forest Environment

      Volume: 61 Issue: 1 Pages: 23-29

    • DOI

      10.18922/jjfe.61.1_23

    • NAID

      130007684588

    • ISSN
      0388-8673, 2189-6275
    • Year and Date
      2019-06-25
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 日本の山地・丘陵地における土層厚マッピングとその不確実性評価2020

    • Author(s)
      山下 尚之、大貫 靖浩
    • Organizer
      日本森林学会第131回大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 秩父地域を対象とした、機械学習によるデジタル土壌マッピングの試み2020

    • Author(s)
      嶋崎 明也、山下 尚之、橋本 昌司、益守 眞也、丹下 健
    • Organizer
      日本森林学会第131回大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Surface soil-thickness mapping and uncertainty estimation in mountainous, upland and hilly area of Japanese archipelago2019

    • Author(s)
      Naoyuki YAMASHITA, Yasuhiro OHNUKI
    • Organizer
      AGU FALL MEETING 2019
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Mapping of soil thickness in mountainous, upland and hilly area of Japan using small-catchment-scale and regional-scale sampling data2019

    • Author(s)
      Naoyuki YAMASHITA, Yasuhiro OHNUKI
    • Organizer
      Pedometrics 2019
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 機械学習を用いた日本の山地部の広域土層厚マッピング2018

    • Author(s)
      山下尚之、大貫靖浩
    • Organizer
      日本土壌肥料学会神奈川大会
    • Related Report
      2018 Research-status Report
  • [Presentation] 北関東の低山帯小流域における表層土層厚マッピング -機械学習手法を用いた広域推定の試み-2018

    • Author(s)
      山下尚之、大貫靖浩
    • Organizer
      日本地形学連合大会
    • Related Report
      2018 Research-status Report
  • [Presentation] 日本の山地小流域における土層厚マッピング手法の開発2018

    • Author(s)
      山下尚之、大貫靖浩
    • Organizer
      第129回日本森林学会
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi