Preprints
https://doi.org/10.5194/egusphere-2022-301
https://doi.org/10.5194/egusphere-2022-301
 
23 May 2022
23 May 2022
Status: this preprint is open for discussion.

Reference Soil Groups Map of Ethiopia Based on Legacy Data and Machine Learning Technique: EthioSoilGrids 1.0

Ashenafi Ali1,2,3,4, Teklu Erkossa2, Kiflu Gudeta1, Wuletawu Abera3, Ephrem Mesfin1, Terefe Mekete1, Mitiku Haile6, Wondwosen Haile7, Assefa Abegaz4, Demeke Tafesse12, Gebeyhu Belay7, Mekonen Getahun8,9, Sheleme Beyene10, Mohamed Assen4, Alemayehu Regassa11, Yihenew G. Selassie9, Solomon Tadesse12, Dawit Abebe13, Yitbarek Walde13, Nesru Hussien1, Abebe Yirdaw1, Addisu Mera1, Tesema Admas1, Feyera Wakoya1, Awgachew Legesse1, Nigat Tessema1, Ayele A. Abebe14, Simret Gebremariam1, Yismaw Aregaw1, Bizuayehu Abebaw1, Damtew Bekele12, Eylachew Zewdie4, Steffen Schulz2, Lulseged Tamene3, and Eyasu Elias1,5 Ashenafi Ali et al.
  • 1Ministry of Agriculture (MoA), Addis Ababa, Ethiopia
  • 2Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ), Ethiopia
  • 3International Centre for Tropical Agriculture (CIAT), Addis Ababa, Ethiopia
  • 4Department of Geography and Environmental Studies, Addis Ababa University (AAU), Addis Ababa, Ethiopia
  • 5Centre for Environmental Science, Addis Ababa University, Ethiopia
  • 6Mekelle University, Mekelle, Ethiopia
  • 7Private Consultant, Addis Ababa, Ethiopia
  • 8Amhara Design and Supervision Enterprise (ADSE), Bahir Dar, Ethiopia
  • 9BahirDar University (BDU), Bahir Dar, Ethiopia
  • 10Hawassa University (HU), Hawassa, Ethiopia
  • 11Jimma University (JU), Jimma, Ethiopia
  • 12Ethiopian Construction Design and Supervision Works Corporation (ECDSWCo), Addis Ababa, Ethiopia
  • 13Oromia Engineering Corporation, Addis Ababa, Ethiopia
  • 14National Soil Testing Centre, MoA, Addis Ababa, Ethiopia

Abstract. Up-to-date digital soil resources information, and its comprehensive understanding, is crucial to support crop production and sustainable agricultural development. Generating such information through conventional approaches consumes time and resources, which is difficult for developing countries. In Ethiopia, the soil resource map that was in use is qualitative, dated (since 1984), and small-scale (1:2 M) which limits its practical applicability. Yet, a large legacy soil profile data accumulated over time and the emerging machine learning modelling approaches can help in generating a high-quality quantitative digital soil map that can provide accurate soil information. Thus, a group of researchers formed a coalition of the willing for soil and agronomy data sharing and collated about 20,000 soil profile data and stored them in a central database. The data were cleaned and harmonized using the latest soil profile data template and prepared 14,681 profile data for modelling. Random Forest was used to develop a continuous quantitative digital map of 18 WRB reference soil groups at 250 m resolution by integrating environmental variables-covariates representing major Ethiopian soil-forming factors. The validated map will have tremendous significance in soil management and other land-based development planning, given its improved spatial nature and quantitative digital representation.

Ashenafi Ali et al.

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on egusphere-2022-301', Sileshi W Gudeta, 24 May 2022 reply
  • AC1: 'Comment on egusphere-2022-301', Ashenafi Ali, 27 Jun 2022 reply
    • CC3: 'Reply on AC1', Sileshi W Gudeta, 10 Jul 2022 reply
      • AC2: 'Reply on CC3', Ashenafi Ali, 13 Jul 2022 reply
  • CC2: 'Comment on egusphere-2022-301', Yitbarek Walde, 06 Jul 2022 reply
    • AC3: 'Reply on CC2', Ashenafi Ali, 01 Sep 2022 reply
  • CC4: 'Comment on egusphere-2022-301', Fuat Kaya, 10 Sep 2022 reply
    • AC4: 'Reply on CC4', Ashenafi Ali, 30 Sep 2022 reply
  • CC5: 'Comment on egusphere-2022-301', Skye Wills, 13 Sep 2022 reply
    • AC5: 'Reply on CC5', Ashenafi Ali, 06 Oct 2022 reply
  • RC1: 'Comment on egusphere-2022-301', Skye Wills, 06 Oct 2022 reply
    • AC6: 'Reply on RC1', Ashenafi Ali, 06 Oct 2022 reply
    • AC7: 'Reply on RC1', Ashenafi Ali, 06 Oct 2022 reply
  • RC2: 'Comment on egusphere-2022-301', Skye Wills, 06 Oct 2022 reply
    • AC8: 'Reply on RC2', Ashenafi Ali, 09 Oct 2022 reply

Ashenafi Ali et al.

Ashenafi Ali et al.

Viewed

Total article views: 1,650 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,090 522 38 1,650 9 11
  • HTML: 1,090
  • PDF: 522
  • XML: 38
  • Total: 1,650
  • BibTeX: 9
  • EndNote: 11
Views and downloads (calculated since 23 May 2022)
Cumulative views and downloads (calculated since 23 May 2022)

Viewed (geographical distribution)

Total article views: 1,497 (including HTML, PDF, and XML) Thereof 1,497 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 30 Nov 2022
Download
Short summary
This paper focuses on collating legacy soil profile data and the production of an updated national soil type map of Ethiopia-EthioSoilGrids version 1.0, using legacy data and a machine learning approach. Given its quantitative digital representation, the map and the associated data have tremendous contributions to agricultural development planning and digital agricultural solutions, as well as improving the accuracy of global predictive soil mapping efforts.