Temporal similarity of the mechanization level and crop yield in Eritrea

Cover Page


Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

BACKGROUND: The dynamics of agricultural production have gradually moved toward mechanization and maximizing efficiency. Understanding the relationship between mechanization and crop yield is crucial to improve productivity.

AIM: This study assesses the temporal pattern similarity between crop yield and the level of mechanization (LOM) and examines how LOM influences crop productivity over time.

MATERIALS AND METHODS: The study used ordinary least squares (OLS) regression with interaction terms for trend analysis and dynamic time warping (DTW) for pattern similarity. Descriptive statistics (standard deviation, mean, minimum, and maximum) and error metrics (MAE and RMSE) were used to assess the DTW distance performance between sequences.

RESULTS: The OLS analysis showed almost parallel trend lines (slopes 0.038% and 0.053%). The DTW analysis showed significant temporal alignment, with a 44.4% perfect match and a similarity score of 34 (34 optimal paths across 28 dataset pairs). Performance evaluation metrics—standard deviation, mean, minimum, and maximum—were 7.56 × 10−3, 1.08 × 10−2, 1.42 × 10−5, and 3.22 × 10−2, respectively. MAE and RMSE values were 6.33 × 10−3 and 7.56 × 10−3, respectively. Based on these values, average similarity, consistency, alignment quality, and error metrics were used to assess the level of similarity. These values indicate high similarity and consistency (based on the low mean DTW distances, standard deviation, and error metrics), despite occasional poor alignment.

CONCLUSION: The temporal similarity between LOM and crop yield showed that variations in LOM significantly impacted cereal crop yields. Agricultural productivity could benefit from mechanization through the use of contemporary technologies, improved supportive policies, and the integration of sustainable practices.

Full Text

Restricted Access

About the authors

Tesfit A. Medhn

Mai-Nefhi College of Engineering and Technology; Russian State Agrarian University — Moscow Timiryazev Agricultural Academy; Addey Agricultural and Food Cooperative

Author for correspondence.
Email: noahtesas@gmail.com
ORCID iD: 0009-0002-4371-1323
SPIN-code: 9344-9472

postgraduate in the Operation of Machinery and Tractor Fleet Department

Eritrea, Asmara; Moscow, Russia; Budapest, Hungary

Alexander G. Levshin

Russian State Agrarian University — Moscow Timiryazev Agricultural Academy

Email: alevshin@rgau-msha.ru
ORCID iD: 0000-0001-8010-4448
SPIN-code: 1428-5710

Dr. Sc. (Engineering), Professor

Russian Federation, Moscow

Simon G. Teklay

Mai-Nefhi College of Engineering and Technology; New Mexico State University

Email: gtsimon1994@gmail.com
ORCID iD: 0009-0002-3336-0523

M. Sc., Graduate Research Assistant, Water Science and Management Program; Department of Animal and Range Sciences; College of Agriculture, Consumer and Environmental Sciences

Eritrea, Asmara; Las Cruces, USA

References

  1. Srivastava A, Goering C, Rohrbach R, Buckmaster D. Engineering principles of agricultural machines. American Society of Agricultural and Biological Engineers; 2006.
  2. Andrew W. Handbook of farm, dairy and food machinery engineering. New York: Elsevier; 2013.
  3. Medhn TA, Teklay SG, Mengstu MT. Analysis of the Level of Agricultural Mechanization in Eritrea Based on USDA Data Sources. European Journal of Agriculture and Food Sciences. 2023;5(6):39–46. doi: 10.24018/ejfood.2023.5.6.664
  4. Abdullatif AAD, Mastrenko NA, Balabanov VI. The results of optimization of the harvesting complex for cleaning are given in the conditions of the Syrian Arab Republic. Agricultural Engineering. 2018;(1 (83)):48–51. doi: 10.26897/1728-7936-2018-1-48-51 EDN: YPMTST
  5. Maistrenko NA, Uvarov VP, Levshin AG, et al. Unification of calculations of productivity of transport and transport and technological equipment. Engineering technologies and systems. 2020;30(4):637–58. doi: 10.15507/2658-4123.030.202004.637-658
  6. Sysoev AM, Erokhin MN, Izmailov AYu, et al. Proposals for Amendments to the Federal Register of Crop Production Technologies (System of Technologies) Taking into Account the Functional Capabilities of the Family of New Agricultural Trucks. Moscow: Vserossiyskiy nauchno-issledovatelskiy institut mekhanizatsii selskogo khozyaystva; 2011.
  7. Bello SR. Agricultural Machinery & Mechanization: Basic Concepts. DPS Dominion publishing services Nigeria; 2012.
  8. Hanayem A, Almohamed S, Alassaf A, Majdalawi M. Socioeconomic Analysis of Soil-Less Farming System — An Comparative Evidence from Jordan, The Middle East. Int J Food Agric Econ. 2022;10: 205–23.
  9. Eritrea Overview: Development news, research, data | World Bank [Internet]. [cited 2023 Feb 9]. Available from: https://www.worldbank.org/en/country/eritrea/overview
  10. Amongo RMC, Onal MKS, Larona MVL, et al. Level of Agricultural Mechanization in Oriental Mindoro, Laguna and Quezon, Philippines Using the Modified Agricultural Mechanization Index for Lowland Rice. Philippine Journal of Agricultural and Biosystems Engineering. 2018; XIV:55–71.
  11. Kiru OK. The agricultural mechanization in Africa: micro-level analysis of state, drivers and effects. In: 6th African Conference of Agricultural Economists. Abuja: Research in agricultural & applied economics; 2019. p. 1–30.
  12. Li W, Wei X, Zhu R, Guo K. Study on factors affecting the agricultural mechanization level in China based on structural equation modeling. Sustainability (Switzerland). 2019;11(1).
  13. Sharma V, Irmak A, Kabenge I, Irmak S. Application of GIS and geographically weighted regression to evaluate the spatial non-stationarity relationships between precipitation vs. Irrigated and rainfed maize and soybean yields. Trans ASABE. 2011;54(3):953–72.
  14. Larrabee B, Scott HM, Bello NM. Ordinary Least Squares Regression of Ordered Categorical Data: Inferential Implications for Practice. 2014. doi: 10.1007/s13253-014-0176-z
  15. John K. M. Kuwornu. Irrigation access and per capita consumption expenditure in farm households: Evidence from Ghana. J Dev Agric Econ. 2012;4(3). doi: 10.5897/JDAE11.105
  16. Ma W, Renwick A, Grafton Q. Farm machinery use, off-farm employment and farm performance in China. Australian Journal of Agricultural and Resource Economics. 2018;62(2):279–98. doi: 10.1111/1467-8489.12249
  17. Tsinaslanidis PE. Subsequence dynamic time warping for charting: Bullish and bearish class predictions for NYSE stocks. Expert Syst Appl. 2018;94:193–204. doi: 10.1016/j.eswa.2017.10.055
  18. Vayer T, Tavenard R, Chapel L, et al. Time Series Alignment with Global Invariances. arXiv. 2020. doi: 10.48550/arXiv.2002.03848
  19. Sakoe H. Dynamic Programming Algorithm Optimization for Spoken Word Recognition. IEEE Trans Acoust. 1978;(1):43.
  20. Cohen S, Luise G, Terenin A, et al. Aligning Time Series on Incomparable Spaces. In: Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, San Diego, California, USA. PMLR; 2021;130.
  21. Halperin T, Ephrat A, Peleg S. Dynamic Temporal Alignment of Speech to Lips. 2018.
  22. Shokoohi Y. M, Hu B, Jin H, et al. Generalizing DTW to the multi-dimensional case requires an adaptive approach. Data Min Knowl Discov. 2017;31(1):1–31. doi: 10.1007/S10618-016-0455-0/FIGURES/20
  23. Kovâcs-Vajna ZM. A fingerprint verification system based on triangular matching and dynamic time warping. IEEE Trans Pattern Anal Mach Intell. 2000;22(11):1266. doi: 10.1109/34.888711
  24. Ruiz AP, Flynn M, Large J, et al. The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov. 2021 Mar 1;35(2):401–49. doi: 10.1007/s10618-020-00727-3
  25. Cassisi C, Montalto P, Aliotta M, et al. Similarity Measures and Dimensionality Reduction Techniques for Time Series Data Mining. In: Advances in Data Mining Knowledge Discovery and Applications.InTech; 2012.
  26. Maus V, Câmara G, Cartaxo R, et al. A Time-Weighted Dynamic Time Warping method for land use and land cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2016;9(8):3729–3739. doi: 10.1109/JSTARS.2016.2517118
  27. Belgiu M, Zhou Y, Marshall M, Stein A. Dynamic time warping for crops mapping. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences — ISPRS Archives. 2020;43(B3):947–51. doi: 10.5194/ISPRS-ARCHIVES-XLIII-B3-2020-947-2020
  28. Mohamedi DM. Assessing the transferability of random forest and time-weighted dynamic time warping for agriculture mapping. 2019.
  29. Rafif R, Kusuma SS, Saringatin S, et al. Crop intensity mapping using dynamic time warping and machine learning from multi-temporal planetscope data. Land (Basel). 2021;10(12).
  30. USDA ERS — International Agricultural Productivity [Internet]. 2023 [cited 2023 Mar 6]. Available from: https://www.ers.usda.gov/data-products/international-agricultural-productivity
  31. Sebastian R. About Feature Scaling and Normalization [Internet]. 2014 [cited 2024 Sep 26]. Available from: https://sebastianraschka.com/Articles/2014_about_feature_scaling.html
  32. Keane M, Neal T. Climate change and U.S. agriculture: Accounting for multidimensional slope heterogeneity in panel data. Quant Econom [Internet]. 2020;11(4):1391–429. [cited 2024 Jun 25] Available from: https://onlinelibrary.wiley.com/doi/full/10.3982/QE1319
  33. Miao X, Zhao D, Lin B, et al. A Differential Protection Scheme Based on Improved DTW Algorithm for Distribution Networks with Highly-Penetrated Distributed Generation. IEEE Access. 2023; 11:40399–411. doi: 10.1109/ACCESS.2023.3269298

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. LOM was horizontally shifted by one year for better analysis, with yield plotted over the years 1993–2020. The broken line represents standardized yield, while the solid line represents LOM.

Download (84KB)
Indexing metadata
3. Fig. 2. Trend Similarity between the LOM (red solid line) and crop yield (dark broken line) over the years 1993–2020.

Download (86KB)
Indexing metadata
4. Fig. 3. DTW distance matching involves repeating or compressing points to minimize the distance between them.

Download (217KB)
Indexing metadata
5. Fig. 4. Optimal similarity path between the LOM and crop yield from 1993 to 2020.

Download (450KB)
Indexing metadata
6. Fig. 1. LOM was horizontally shifted by one year for better analysis, with yield plotted over the years 1993–2020. The broken line represents standardized yield, while the solid line represents LOM.

Download (160KB)
Indexing metadata
7. Fig. 2. Trend Similarity between the LOM (red solid line) and crop yield (dark broken line) over the years 1993–2020.

Download (150KB)
Indexing metadata
8. Fig. 3. DTW distance matching involves repeating or compressing points to minimize the distance between them.

Download (252KB)
Indexing metadata
9. Fig. 4. Optimal similarity path between the LOM and crop yield from 1993 to 2020.

Download (582KB)
Indexing metadata

Copyright (c) 2025 Eco-Vector


 СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: ПИ № ФС 77 - 81900 выдано 05.10.2021.