In this study, we describe the seed imbibition of 14 different species, from crop, forest, and native species potentially able to recover landscapes and form sustainable green cities. Seed imbibition is a fundamental physical and physiological process for reactivating metabolism and hydrolytic enzymes that will provide seed germination. We verified that the water imbibition is more closely governed by differences between osmotic potential (Ψ_w) and surrounding media than seed weight or seed hardness. In turn, seeds of Spondias tuberosa and Euterpe oleracea that have a Ψ_w of −75 MPa and a tegument as hard as 200 N imbibed an insignificant volume of water. Consequently, their metabolism is not significantly affected comparing the non-imbibed seeds and 120-h-imbibed seeds. Malpighia glabra or Annona squamosa also show very negative Ψ_w where the seed coat hardness is less evident; however, in these species, the seed imbibition increased the respiration rate by eight- to ten-fold in 120 h-imbibed-seeds than non-imbibed-seeds. The high-water absorption in M. glabra (49%) seems to be due to its highly convoluted tissue in the dry state, while in J. curcas and A. squamosa the presence of a highly porous seed coat must have favored seed imbibition and prompt metabolic reactivation.

Pests and diseases significantly impact the quality and yield of maize. As a result, it is crucial to conduct disease diagnosis and identification for timely intervention and treatment of maize pests and diseases, ultimately enhancing the quality and economic efficiency of maize production. In this study, we present an enhanced maize pest identification model based on ResNet50. The objective was to achieve efficient and accurate identification of maize pests and diseases. By utilizing convolution and pooling operations for extracting shallow-edge features and compressing data, we introduced additional effective channels (environment–cognition–action) into the residual network module. This step addressed the issue of network degradation, establishes connections between channels, and facilitated the extraction of crucial deep features. Finally, experimental validation was performed to achieve 96.02% recognition accuracy using the ResNet50 model. This study successfully achieved the recognition of various maize pests and diseases, including maize leaf blight, Helminthosporium maydis, gray leaf spot, rust disease, stem borer, and corn armyworm. These results offer valuable insights for the intelligent control and management of maize pests and diseases.