Conservation agriculture with use of crop rotations and residue management provides many benefits to the soil and environment, which vary depending on climatic and soil conditions, crops between of the rotation, and the amount of incorporated residue. The present study evaluated the effect of two medium-term of canola (Brassica napus L.)-wheat (Triticum aestivum L.) and bean (Phaseolus vulgaris L.)-wheat rotations with four residue incorporation rates of preceding crop (0, 50, 100, and 200%) on wheat grain yield and nutrient concentrations; Nitrogen (N), Phosphorous (P), Potassium (K), Calcium (Ca), Magnesium (Mg) and Sulfur (S) at the end of the fourth season in a volcanic soil in south-central Chile. Grain yield varied between 5.77 and 5.96 Mg ha⁻¹ and was not affected by the preceding crop. The residue incorporation rates had no effect on the evaluated parameters. The preceding crop affected grain K and Mg concentration, which increased after bean. The Ca concentration in the residue was positively affected by the canola crop. Total macronutrient extraction in the wheat crop was 444.1 kg ha⁻¹. The ranking of total macronutrient extraction in the wheat crop was N > K > P > Ca > S > Mg with means of 198–221, 26.1–30.6, 133–163, 20.8–27.1, 13.4–16.5, and 14.9–16.5 kg ha⁻¹, respectively.

Drought significantly constrains common bean (Phaseolus vulgaris L.) production worldwide, and as climate change intensifies, projections indicate a subsequent reduction in yield. This study aimed to identify drought-resilient genotypes among twenty common bean lines in Chile under two water regimes: regular irrigation and terminal drought stress. The research was conducted over two seasons in south-central Chile. Drought significantly reduced grain yield (22.7%), aboveground biomass (37%), harvest index (19.5%), the number of grains per pod (61.3%), and hundred-grain weight (10.1%). Genotypes 452, 473, and 483 exhibited minimal yield reductions (<11%) and maintained stable physiological performance, including higher quantum yield of photosystem II and efficient photoprotective mechanisms (increased ΦNPQ) under stress. In contrast, sensitive genotypes like Blanco Español showed marked yield loss (54%) and lower photosynthetic efficiency. Chlorophyll retention emerged as a key trait for identifying high-yielding, drought-tolerant genotypes. Drought also accelerated crop maturation in susceptible genotypes, compromising yield potential. These findings highlight the importance of integrating agronomic, phenological, and physiological traits in breeding programs to develop drought-adapted varieties. The tolerant genotypes offer valuable genetic traits to improve drought resilience and contribute to food security in the face of climate change.

Crop rotations and residue management contributes to the sustainability of the soil and environment and reduction of fertiliser use. However, appropriate crop and residue level combinations have yet to be determined to maximise productivity, while ensuring the preservation of soil resources in different agricultural production systems. The experiment evaluated production and soil chemical properties in bean after three preceding crops (bread wheat, durum wheat, and corn) with four residue incorporation levels (0%, 50%, 100%, and 200%) under irrigation conditions in volcanic soil in south central Chile. A split plot design with four replicates was used. Results indicated that the production of grain and crop residue of bean were higher after corn and durum wheat. The preceding crop also affected some soil chemical properties, especially after the corn crop. The production parameters were not affected by the different residue levels; these had a positive effect on the concentrations of N, K, and Mg and an effect that was directly proportional to the residue level being used. Correlations between soil chemical properties were also established, consistently highlighting the increase in the concentration of the nutrients N, K, Ca, and Mg associated with increases in organic matter content.

Climate change is reshaping weed population dynamics, creating non-stationary management challenges for which static decision rules are insufficient. This chapter presents and evaluates an open surveillance toolkit of artificial intelligence tools for recognizing and mapping Ambrosia artemisiifolia (common ragweed) at complementary spatial scales, tested across two phenological phases (seedling, September 2024; adult, December 2024) in a lentil paddock in central Chile. At the field scale, a YOLOv11 detection model coupled with Slicing Aided Hyper Inference achieved mAP50 of 0.886. Cross-domain experiments revealed that single-site models collapse catastrophically when deployed in new geographies (mAP50 dropping to 0.108), but multi-domain training recovers performance to 0.874. At the satellite scale, PRESTO foundation model embeddings correlated strongly with ground-truth weed density (r = 0.739); geographically weighted regression explained up to 91% of local density variance. All methods are released as the ragweed-ai-toolkit ( https://github.com/agroia-lab/ragweed-ai-toolkit ), a modular open-source Python package enabling adaptation to new species and geographies.

Conservation practices in agriculture using crop rotations and residue management benefit the productivity; these can vary depending on climate and soil conditions, crops, and amount of incorporated residue. The present study evaluated the effect of two biannual rotations; canola (Brassica napus L.) – corn (Zea mays L.) and bean (Phaseolus vulgaris L.) – corn rotations with four residue incorporation rates (0%, 50%, 100%, and 200%) of the preceding crop on corn grain yield, residue production, and nutrient concentration and extraction after two rotation cycles in a volcanic soil of moderate depth in south-central Chile. Grain yield varied between 17.04 and 17.40 Mg/ha, residue production between 16.41 and 16.50 Mg/ha. The preceding crop affected concentration and extraction of some nutrients in both grain and residue. The residue rate affected both concentration and extraction of some nutrients only in the grain. The Ca distribution to the corn grain was negatively affected by both the preceding bean crop and increasing residue incorporation rate. The ranking of total macronutrient extraction in the corn crop was K > N > Ca > P > Mg > S. The extraction means ranged from 320 to 326, 56.0 to 57.1, 365 to 374, 86.5 to 99.3, 39.4 to 42.4, and 22.6 to 23.7 kg/ha, whereas grain nutrient distribution coefficients ranged from 64.5 to 66.8, 90.1 to 90.9, 23.1 to 23.7, 1.3 to 2.0, 50.8 to 57.5, and 60.3 to 60.6 for N, P, K, Ca, Mg and S, respectively.

Sustainable weed management in lentil (Lens culinaris Medik.) production requires accurate knowledge of weed spatial distribution and the site-specific factors influencing infestation patterns. Limited pre- and post-emergence herbicide options for pulse crops underscore the need for precise pre-emergence applications guided by spatially explicit weed mapping. This study integrates YOLOv11 object detection with Slicing-Aided Hyper Inference (SAHI) framework, advanced geostatistical techniques, and soil electromagnetic induction measurements to develop a comprehensive precision agriculture framework for species-specific weed management. High-resolution drone imagery (4K, 1.5 m altitude) was systematically collected across a 3.42-hectare commercial lentil field in Chile’s Central Irrigated Valley, complemented by satellite-derived vegetation indices (Sentinel-2 NDVI) and soil electrical conductivity mapping (EM38-MK2). The YOLOv11 model achieved robust detection performance with F1-scores of 0.87 for lentil crops and 0.84 for Ambrosia artemisiifolia, the dominant weed species, enabling species-specific density mapping at 5 m × 5 m resolution. Geostatistical analysis revealed significant spatial autocorrelation in weed distributions (Moran’s I = 0.667, p < 0.001) with strong bivariate associations between weed density and environmental variables, particularly soil electrical conductivity (spatial r = 0.633) and vegetation indices (spatial r = 0.818). Fuzzy clustering successfully delineated four distinct management zones, with 31.9% of the field requiring critical intervention and 51.7% suitable for maintenance-level management, enabling potential 35-50% reduction in herbicide use while maintaining effective weed control. The demonstrated multi-scale approach enables transition from satellite-guided field reconnaissance to ultra-precise drone-based treatments, supporting cost-effective implementation across extensive agricultural areas. This integrated AI-geostatistical framework addresses critical limitations in current precision agriculture technologies by combining high-accuracy species detection with spatial analysis capabilities that enable predictive modelling and evidence-based management optimisation, establishing foundations for scalable precision weed management in sustainable agricultural production systems.