The Chincha Kingdom likely used seabird guano to fertilize their corn. Breakthroughs, discoveries, and DIY tips sent six days a week. When it comes to the success of ancient civilizations, the first things that come to mind are typically their military strength, roads, and trade. New research, however, highlights a potential key to the strength of a pre-Incan society that is both surprising and slightly disgusting: seabird guano, also known as bird poop. The successful power in question is the Chincha Kingdom (1000 - 1400 CE), a coastal society that ruled over the Chincha Valley in present-day southern Peru.

The space-inspired wastewater treatment uses the nutrients and loses the odor. Breakthroughs, discoveries, and DIY tips sent every weekday. When most people need to go number one, they find the nearest bathroom and don't give half a thought to what happens to their pee once it disappears down the toilet or urinal . It turns out that the nitrogen in human urine can be used in fertilizer. However, humanity's use of nitrogen is everything but efficient, according to a pair of siblings who founded the Swiss start-up company, VunaNexus.

Environment Conservation Land World's first mushroom-powered toilet could replace stinky porta-potties Breakthroughs, discoveries, and DIY tips sent every weekday. How many times have you needed to use the restroom, only to discover that the only available one was a portable toilet? Suddenly, you actually don't need to go badly . We don't blame you--they look bad, smell awful, and produce toxic waste. Now, researchers from the University of British Columbia (UBC) in Canada have a solution.

Agricultural decision-making involves complex, context-specific reasoning, where choices about crops, practices, and interventions depend heavily on geographic, climatic, and economic conditions. Traditional large language models (LLMs) often fall short in navigating this nuanced problem due to limited reasoning capacity. We hypothesize that recent advances in large reasoning models (LRMs) can better handle such structured, domain-specific inference. To investigate this, we introduce AgReason, the first expert-curated open-ended science benchmark with 100 questions for agricultural reasoning. Evaluations across thirteen open-source and proprietary models reveal that LRMs outperform conventional ones, though notable challenges persist, with the strongest Gemini-based baseline achieving 36% accuracy. We also present AgThoughts, a large-scale dataset of 44.6K question-answer pairs generated with human oversight and equipped with synthetically generated reasoning traces. Using AgThoughts, we develop AgThinker, a suite of small reasoning models that can be run on consumer-grade GPUs, and show that our dataset can be effective in unlocking agricultural reasoning abilities in LLMs. Our project page is here: https://baskargroup.github.io/Ag_reasoning/

Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive, time-consuming and expensive. In most cases, it is not feasible to gather crop state measurements before every decision moment. Moreover, in previous research pertaining to farm management optimization, these observations are often assumed to be readily available without any cost, which is unrealistic. Hence, enabling optimization without the need to have temporally complete crop state observations is important. An approach to that problem is to include measuring as part of decision making. As a solution, we apply reinforcement learning (RL) to recommend opportune moments to simultaneously measure crop features and apply nitrogen fertilizer. With realistic considerations, we design an RL environment with explicit crop feature measuring costs. While balancing costs, we find that an RL agent, trained with recurrent PPO, discovers adaptive measuring policies that follow critical crop development stages, with results aligned by what domain experts would consider a sensible approach. Our results highlight the importance of measuring when crop feature measurements are not readily available.

Virginia farmer John Boyd Jr., weighs in on a watchdog's satellite tracking methane emissions and a provision in the omnibus bill that allocates funds for electronically tracking livestock. There is one thing that distinguishes 60-year-old Vo Van Van's rice fields from a mosaic of thousands of other emerald fields across Long An province in southern Vietnam's Mekong Delta: It isn't entirely flooded. Using less water and using a drone to fertilize are new techniques that Van is trying and Vietnam hopes will help solve a paradox at the heart of growing rice: The finicky crop isn't just vulnerable to climate change but also contributes uniquely to it. Rice must be grown separately from other crops and seedlings have to be individually planted in flooded fields; backbreaking, dirty work requiring a lot of labor and water that generates a lot of methane, a potent planet-warming gas that can trap more than 80-times more heat in the atmosphere in the short term than carbon dioxide. A large drone carrying fertilizer flies over Vo Van Van's rice fields in Long An province in southern Vietnam's Mekong Delta, on Jan. 23, 2024.

As the global population soars past 8 billion people, the world faces a conundrum: There are more of us to feed, but our food needs to be grown on the same amount of land, if not less. At CES 2023, John Deere is pushing for a future in which farming relies ever more on sensors and machine learning technologies to meet those needs. When you add in the realities of a changing climate that is shifting growing seasons and making weather patterns less predictable, it's clear that the farm of the future will require radical change. John Deere's latest foray into high-tech agriculture is a sensor-driving robotic technology called ExactShot that's designed to reduce fertilizer use by as much as 60%, saving farmers money and slashing the amount of excess chemicals that go into the ground. John Deere is bringing more robots into the farm field with new technology that can precisely fertilize individual seeds. Instead of shooting a steady stream of fertilizer into the soil over the seeds as they're planted in rows by machinery, the company's ExactShot technology uses sensors and robotics to send out timed bursts of fertilizer that coat individual seeds, leaving the spaces between them fertilizer-free.

The global population is growing at an alarming rate, and with it comes the challenge of finding new ways of producing enough food to feed everyone. The current state of the food production industry calls for a shift in strategy if we want to ensure that everyone has access to healthy and nutritious food in the future. Artificial intelligence (AI) is one of the key tools we need to achieve this goal. With AI, we can tackle complex problems, optimize processes, and produce results that would be much harder or even impossible to do manually. In this article, we will explore how AI will change how we feed the world, offer some valuable insights to farmers, and show where AI currently succeeds in food production and where it still has its limitations.

As the global population has expanded over time, modernizing agriculture with the aid of innovations like AI has been humanity's prevailing approach to staving off famine. A variety of mechanical and chemical innovations delivered during the 1950s and 1960s represented the third agricultural revolution. The adoption of pesticides, fertilizers and high-yield crop breeds, among other measures, transformed agriculture and ensured a secure food supply for many millions of people over several decades. Concurrently, modern agriculture has emerged as a culprit of global warming, responsible for one-third of greenhouse gas emissions, namely carbon dioxide and methane. Meanwhile, inflation on the price of food is reaching an all-time high, while malnutrition is rising dramatically.

Seven years have passed since world leaders met in New York and agreed on 17 Sustainable Development Goals (SDGs) to resolve major challenges including poverty, hunger, inequality, climate change and health. The pandemic undoubtedly diverted attention from some of these issues in the past couple of years. But even before COVID-19, the United Nations was warning that progress to meet the SDGs was not advancing at the speed or on the scale needed. Meeting them by 2030 will be tough. The pandemic demonstrated like nothing else the power of working collaboratively, across borders, for the benefit of society.