Crop simulation models are widely used as research tools to explore the impact of various technologies and compliment field experimentation. Machine learning (ML) approaches have emerged as promising artificial intelligence alternative and complimentary tools to the commonly used crop production models. The study was designed to answer the following questions: (a) Can machine learning techniques predict maize grain yields under conservation agriculture (CA)? (b) How close can ML algorithms predict maize grain yields under CA-based cropping systems in the highlands and lowlands of Eastern and Southern Africa (ESA)? Machine learning algorithms could predict maize grain yields from conventional and CA-based cropping systems under low and high potential conditions of the ESA region. Linear algorithms (LDA and LR) predicted maize yield more closely to the observed yields compared with nonlinear tools (NB, KNN, CART and SVM) under the conditions of the reported study. However, the KNN algorithm was comparable in its yield prediction to the linear tools tested in this study. Overall, the LDA algorithm was the best tool, and SVM was the worst algorithm in maize yield prediction. Evaluating the performance of different ML algorithms using different criteria is critical in order to get a more robust assessment of the tools before their application in the agriculture sector.

Continuous conventional tillage coupled with unsystematic cereal/legume rotations has promoted low crop productivity on smallholder farms. A multi-locational study was established in three agro-ecoregions (AEs) of Zimbabwe. The aim of the study was to determine the effect of four tillage systems (conventional plowing, planting basins, rip-line and animal traction direct seeding systems) on maize (Zea mays L.), cowpea [Vigna unguiculata (L.) Walp] and soybean [Glycine max (L.) Merrill] yields, and evaluate the economic performance of the conservation agriculture (CA) systems relative to conventional plowing. Each farmer was a replicate of the trial over the three cropping seasons. In the high (750–1000 mm per annum) and low (450–650 mm) rainfall AEs, conventional practice and CA systems gave similar maize grain yield. Under medium rainfall conditions (500–800 mm) planting basins, rip-line and direct seeding systems gave 547, 548 and 1690 kg ha⁻¹ more maize yield than the conventional practice. In the high and low rainfall AEs, conventional practice and planting basins had the lowest maize production risk. Cowpea yield was 35 and 45% higher in the rip-line and direct seeding than conventional practice. Soybean yield was higher in rip-line (36%) and direct seeding (51%) systems than conventional practice. Direct seeding system gave the highest net benefits in all AEs. A combination of long-term biophysical and socio-economic assessments of the different cropping systems tested in our study is critical in order to fully understand their performance under different AEs of Zimbabwe.

Agriculture is threatened by ever increasing temperatures and this trend is predicted to continue for the near and distant future. The negative impact of rising temperatures on agri-food systems is also compounded by the erratic and highly variable rainfall in most parts of southern Africa. Minimum and maximum temperatures’ variability and trend analysis were undertaken using daily time series data derived from 23 meteorological stations spread across Malawi, Mozambique, South Africa and Zimbabwe. The modified Mann–Kendall and Theil–Sen slope models were used to assess temperature trends and their magnitudes. Temperature varied with location and minimum temperature was more variable than maximum temperature. Semi-arid regions had higher variation in minimum temperature compared to humid and coastal environments. The results showed an upward trend in minimum (0.01–0.83 °C over a 33–38 year period) and maximum (0.01–0.09 °C over a 38–57 year period) temperatures at 9 and15 locations, respectively. A downward trend in minimum temperature (0.03–0.20 °C over 38–41 years) occurred in South Africa at two locations and Dedza (Malawi), while a non-significant decline in maximum temperature (0.01 °C over 54 years) occurred at one location in coastal dry sub-humid Mozambique. The results confirm the increase in temperature over 33–79 years, and highlight the importance of including temperature when designing climate change adaption and mitigation strategies in southern Africa and similar environments.

SUMMARY: Multilocation experiments were established to determine the best strategy for using inorganic fertilizer in conservation agriculture (CA) systems that use green manure cover crops, namely sunhemp, velvet bean and cowpea grown in rotation with maize. The objectives of the study were to determine (i) the effect of half and full rates of basal fertilizer on maize and legume biomass yields, (ii) the residual effects of unfertilized, half and fully fertilized green manure legumes on maize grown after the legumes, and (iii) the residual effect of unfertilized, half and fully fertilized green manure legumes combined with basal and topdressing fertilizer on maize yields. Experimental design was a randomized complete block with basal fertilizer as a treatment in the green manure legumes phase. Previously, in the maize phase, green manure legume species were the main treatment with basal fertilizer as a subtreatment (sunhemp, velvet bean and cowpea: 0, 75, 150 kg ha⁻¹and 0, 50, 100 kg ha⁻¹, respectively). Nitrogen was applied in the maize phase at 0, 23, 46, 69 kg N ha⁻¹as a sub-subtreatment in Malawi. Results showed that inorganic fertilizer is the most effective when applied to the maize, not green manure legumes. Biomass of green manure legumes, sunnhemp 8084 kg ha⁻¹, velvet bean 7678 kg ha⁻¹and cowpea 4520 kg ha⁻¹, was not significantly affected by application of basal fertilizer. Maize production increased after the application of green manure legumes with maize-after-maize, maize-after-velvet bean, maize-after-sunnhemp and maize-after-cowpea, yielding 3804, 5440, 5446 and 5339 kg ha⁻¹, respectively. Nitrogen increased maize yield regardless of the previously used green manure legumes species. Our results suggest that farmers should apply fertilizer to maize and grow green manure legumes on residual soil in CA systems. Despite growing green manure legumes, smallholders should apply nitrogen topdressing to maize grown using the green manure legumes in some agro-ecologies.

A long-term study was carried out in the Zidyana Extension Planning Area (EPA), Malawi and in the Zimuto Communal Area, Zimbabwe, to evaluate the effect of different conservation agriculture (CA) systems on crop productivity, soil quality and economic performance. Maize productivity results from Zidyana showed that CA systems out-yielded the conventional system in seven out of nine cropping seasons. Labour savings relative to the conventional control ranged from 34–42 labour days ha⁻¹ due to reduced time needed to make manual ridges and for weed control, leading to higher net benefits of 193–444 USD·ha⁻¹. In Zimuto, yield benefits were apparent from the second season onwards and there was a much clearer trend of increased yields of CA over time. Greater net benefits (in USD·ha⁻¹) were achieved on CA systems in Zimuto compared with conventional control treatments due to overall higher yields from CA systems. In Zimuto, both increased infiltration and a gradual increase in soil carbon were recorded, which may have contributed to the greater yield response of CA in this area. In Zidyana, yield increases were attributed primarily to enhanced water infiltration since no increases in soil carbon levels were measured. Farmers highlighted critical challenges to the adoption of CA. These will have to be addressed in future research and extension to provide effective solutions to farmers.